🧹 Awesome LLM Unlearning
A curated collection of papers, surveys, benchmarks, frameworks, and blog posts for machine unlearning in large language models.
As of the last commit, there are 651 papers, 19 surveys and position papers, 3 frameworks, and 2 blog posts.
If you believe your paper on LLM unlearning is not included, or if you find a mistake, typo, or information that is not up to date, please open an issue or submit a pull request, and I will be happy to update the list.
Contents
Papers
2026
- SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
- Author(s): Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham, Kwok-Yan Lam
- Date: 2026-10
- Venue: -
- Code: -
- LLM Persona Unlearning
- Author(s): Kemou Li, Zhuan Shi, Qizhou Wang, Fengpeng Li, Negar Rostamzadeh, Golnoosh Farnadi, Jiantao Zhou
- Date: 2026-09
- Venue: -
- Code: -
- Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing
- Author(s): Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi, Masashi Sugiyama, Jiantao Zhou
- Date: 2026-09
- Venue: -
- Code: -
- Learning What to Forget: Distributional Unlearning for LLM Representation Spaces
- Author(s): Pinaki Mohanty, Haoran Tang, Maggie Makar, Rajiv Khanna
- Date: 2026-09
- Venue: -
- Code: -
- Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
- Author(s): Haoran Tang, Rajiv Khanna
- Date: 2026-09
- Venue: -
- Code: -
- Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
- Author(s): Tianhao Qian, Ziming Hong, Chongyang Gao, Kezhen Chen, Lixu Wang
- Date: 2026-09
- Venue: -
- Code: -
- UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?
- Author(s): Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen
- Date: 2026-09
- Venue: -
- Code: -
- Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
- Author(s): Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong
- Date: 2026-09
- Venue: -
- Code:
- UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
- Author(s): Zhengyang Shan, Jiayun Xin, Yanjun Lin, Xu Qian, Zhiang Liu, Minghui Xu, Yue Zhang, Qin Hu, Kun Li, Xiuzhen Cheng
- Date: 2026-09
- Venue: -
- Code: -
- TULIP: Targeted LLM Unlearning at Layers Identified Per-Input
- Author(s): Yejin Kim, William F. Shen, Seokwon Jung, Daeun Park, Seong Joon Oh
- Date: 2026-09
- Venue: -
- Code: -
- Causal Routing for Unlearning
- Author(s): Bardh Prenkaj, Andrea D'Angelo, Davide Mottin, Federico Fontana, Davide Gabrielli, Paola Velardi, Stefano Faralli
- Date: 2026-09
- Venue: -
- Code: -
- Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths
- Author(s): Jialu Wang, Peizhi Niu, Haoteng Yin, Hans Hao-Hsun Hsu, Pan Li, Rongzhe Wei
- Date: 2026-09
- Venue: -
- Code: -
- RADNPO: Reference-free Adaptive Negative Preference Optimization for LLM Unlearning
- Author(s): Shenghan Tan, Ziyi Zhou, Wenpeng Hu, Mengyuan Zhang
- Date: 2026-09
- Venue: -
- Code: -
- Trajectory Unlearning on LLM-based Agents
- Author(s): Yingdan Shi, Ren Wang
- Date: 2026-09
- Venue: -
- Code: -
- LLM Unlearning Evaluation with TRIAGE
- Author(s): Danial Ataee, Peter Triantafillou
- Date: 2026-09
- Venue: -
- Code: -
- Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders
- Author(s): Itai Zehavi, Fanny Jourdan, Ulrich Aivodji
- Date: 2026-09
- Venue: -
- Code: -
- The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning
- Author(s): Manit Baser, Aditya Nawal, Dinil Mon Divakaran, Mohan Gurusamy
- Date: 2026-09
- Venue: -
- Code: -
- Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
- Author(s): Jialu Wang, Jianing Deng, Shuqing Luo, Yuanzhe Li, Dongwei Wang, Jingtong Hu, Huanrui Yang, Song Wang, Tianlong Chen
- Date: 2026-09
- Venue: -
- Code: -
- What Was Once Learned May Need to Be Unlearned: Machine Unlearning for Deprecated API Knowledge in Large Language Models
- Author(s): Jin Liu, Yanzhong He, Guancheng Lin, Xiao Liu, Jacky Wai Keung, Xiao Yu, Xiaoxue Ma
- Date: 2026-09
- Venue: -
- Code: -
- GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
- Author(s): Zeyu Yan, Guanghao Zhou, Minghui Qiu, Ming Gao, Cen Chen
- Date: 2026-09
- Venue: -
- Code:
- $\mu^2$-Bench: A Multilingual Machine Unlearning Benchmark
- Author(s): Kyomin Hwang, Hyeonjin Kim, Hyunho Lee, Yearim Kim, Yeji Song, Nojun Kwak
- Date: 2026-09
- Venue: -
- Code: -
- Test-Time Unlearning via Sparse Autoencoder
- Author(s): Pingzhi Li, Jinhao Duan, Vaishnav Tadiparthi, Nakul Agarwal, Kwonjoon Lee, Ehsan Moradi Pari, Hossein Nourkhiz Mahjoub, Sijia Liu, Tianlong Chen
- Date: 2026-09
- Venue: -
- Code: -
- Machine Unlearning for Speech Question Answering in Large Audio-Language Models
- Author(s): Zhe Liu
- Date: 2026-09
- Venue: -
- Code: -
- K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments
- Author(s): Guangsheng Yu, Yanna Jiang, Qin Wang, Baihe Ma, Xu Wang
- Date: 2026-09
- Venue: -
- Code: -
- Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
- Author(s): Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou
- Date: 2026-09
- Venue: -
- Code:
- When Retain Constraints Conflict: Mitigating Forget-Retain Interference in Tabular Data
- Author(s): Zijie Liu, Jinhao Duan, Bingqi Shang, Xinming An, Sijia Liu, Tianlong Chen
- Date: 2026-09
- Venue: -
- Code: -
- Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning
- Author(s): Pengyang Shao, Chuanpeng Lu, Wei Qin, Yanzheng Jin, Xiaohao Liu, Xi Ai, Kenji Kawaguchi, Richang Hong
- Date: 2026-09
- Venue: -
- Code:
- Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
- Author(s): Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He
- Date: 2026-09
- Venue: -
- Code: -
- Extracting Forgotten Prompts from Targeted Unlearned Models
- Author(s): Au Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen, Nicholas D. Lane, Ligang He
- Date: 2026-09
- Venue: -
- Code: -
- Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
- Author(s): Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee
- Date: 2026-09
- Venue: -
- Code: -
- Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
- Author(s): Kangwook Ko, Jaehyuk Jang, Wonjun Lee, Hee-Seon Kim, Changick Kim
- Date: 2026-08
- Venue: -
- Code: -
- Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
- Author(s): Aditi Sarker, Nazreen Shah, Rafi Ibn Sultan, Rhongho Jang, Dongxiao Zhu, Prashant Khanduri
- Date: 2026-08
- Venue: -
- Code: -
- On the Recoverability of Private Information Unlearning in Large Language Models
- Author(s): Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao
- Date: 2026-08
- Venue: -
- Code:
- GRACE:Gradient-guided Coreset Selection for LLM Unlearning
- Author(s): Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro, Tommaso Cucinotta
- Date: 2026-08
- Venue: -
- Code: -
- AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning
- Author(s): Wonjun Lee, Jaehyuk Jang, Kangwook Ko, Hee-Seon Kim, Changick Kim
- Date: 2026-08
- Venue: -
- Code: -
- A Model Merging Approach for Continual MLLM Unlearning
- Author(s): Yuhang Wang, Linlin Zhang, Haoxuan Ji, Xianmin Ye, Zhenxing Niu, Haichang Gao
- Date: 2026-08
- Venue: -
- Code: -
- Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness
- Author(s): Haoting Qian, Qingjie Zhang, Zhicong Huang, Cheng Hong, Han Qiu
- Date: 2026-08
- Venue: -
- Code: -
- Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
- Author(s): Chunlin Liu, Junnian Chen, Haitong Jiang, Jianyu Zhao, Yingsen Pang, Jingchen Li, Jiabiao He, Youming Lu, Jinhe Bi, Yuntao Du
- Date: 2026-08
- Venue: -
- Code: -
- Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
- Author(s): Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Haoran Luo, Jiapu Wang, Qing Yang, Jingwei Zhang
- Date: 2026-08
- Venue: -
- Code: -
- Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models
- Author(s): Junxiang You, Junkai Chen, Yuhao He, Ruiqi Liu, Zhetao Guo, Shu Wu
- Date: 2026-08
- Venue: -
- Code: -
- Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
- Author(s): Junkai Lin, Junkai Chen, Siqi Hou, Yuhao He, Ruiqi Liu, Chenhan Jin, Shengze Xu, Tieyong Zeng
- Date: 2026-08
- Venue: -
- Code: -
- Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning
- Author(s): Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj, Gjergji Kasneci
- Date: 2026-07
- Venue: ECML-PKDD 2026 WIPE-OUT Workshop
- Code: -
- Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
- Author(s): Xiangyu Yin, Jiaxu Liu, Zhen Chen, Chih-Hong Cheng
- Date: 2026-07
- Venue: -
- Code: -
- Subtract or Replay? Exact Deletion from Language-Model Memory
- Author(s): Vishwajith Ramesh
- Date: 2026-07
- Venue: -
- Code: -
- Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS
- Author(s): Viktoriia Makovska, George Fletcher
- Date: 2026-07
- Venue: -
- Code: -
- Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
- Author(s): Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci
- Date: 2026-07
- Venue: -
- Code: -
- Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification
- Author(s): Sen Yang, Yuen-Hei Yeung
- Date: 2026-07
- Venue: -
- Code: -
- Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
- Author(s): Zijie Liu, Jinhao Duan, Gaowen Liu, Sijia Liu, Tianlong Chen
- Date: 2026-07
- Venue: -
- Code: -
- One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models
- Author(s): Sudharshan Balaji, Yili Ren, Guangjing Wang, Yimin Chen, Ning Wang
- Date: 2026-07
- Venue: -
- Code: -
- LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
- Author(s): Ruppikha Sree Shankar, Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan, Troy Paulus Asia, Saptarshi Sengupta
- Date: 2026-07
- Venue: -
- Code: -
- HermesHFL: Incentive-Compatible Hierarchical Federated Unlearning for Dynamic LLM Fine-Tuning
- Author(s): Chenxi Sun, Minghui Liwang, Wusi He, Zhang Liu, Yuhan Su, Seyyedali Hosseinalipour, Xianbin Wang, Yiguang Hong
- Date: 2026-07
- Venue: -
- Code: -
- Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
- Author(s): Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein
- Date: 2026-07
- Venue: -
- Code:
- Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
- Author(s): Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil
- Date: 2026-07
- Venue: -
- Code:
- POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
- Author(s): Zhangheng LI, Jianing Zhu, Junyuan Hong, Sungmin Eum, Shuowen Hu, Suya You, Zhangyang Wang
- Date: 2026-07
- Venue: -
- Code: -
- MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs
- Author(s): Shubhadip Nag, Srinjoy Das, Agniva Saha, Anushree Ghosh, Soumi Das, Tarun Kumar, Suparna Bhattacharya, Sourangshu Bhattacharya
- Date: 2026-07
- Venue: -
- Code: -
- PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
- Author(s): Xianren Zhang, Delvin Ce Zhang, Dongwon Lee, Suhang Wang
- Date: 2026-07
- Venue: -
- Code: -
- LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
- Author(s): Matteo Boglioni, Thibault Rousset, Siva Reddy, Marius Mosbach, Verna Dankers
- Date: 2026-07
- Venue: -
- Code: -
- Auditing Forgetting in Limited Memory Language Models
- Author(s): Arya Raeesi, Hanna Roed
- Date: 2026-07
- Venue: -
- Code: -
- Selective Span-Level Unlearning for Large Language Models
- Author(s): Chaewon Yoon, Dongjun Kim, Hyun-Je Song
- Date: 2026-07
- Venue: ACL 2026
- Code: -
- The Silence of the Facts: Popularity as a Barrier to Machine Unlearning
- Author(s): Anna Borisiuk, Andrey Savchenko, Alexander Panchenko, Elena Tutubalina
- Date: 2026-07
- Venue: ACL 2026 SRW
- Code: -
- Thesis Proposal: Targeted and Unified Cross-Lingual Unlearning from Multilingual Language Models
- Author(s): Jan Bronec, Jindřich Helcl
- Date: 2026-07
- Venue: ACL 2026 SRW
- Code: -
- Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law
- Author(s): Noah Scharrenberg, Chang Sun
- Date: 2026-06
- Venue: -
- Code: -
- Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs
- Author(s): Huy Q. Tran, Dang H. Vu, Tuyen N. Dinh, Anh H. D. Nguyen, Anh N. H. Vu, Anh M. T. Bui, Phuong T. Nguyen
- Date: 2026-06
- Venue: -
- Code: -
- CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence
- Author(s): Zhiqiang Xie, Yijing Lin, Zhipeng Gao, Dong In Kim
- Date: 2026-06
- Venue: -
- Code:
- Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
- Author(s): Poojitha Thota, Shirin Nilizadeh
- Date: 2026-06
- Venue: -
- Code: -
- Uncertainty-based Debiasing and Unlearning for Decontamination
- Author(s): Guangzhi Sun, Xiao Zhan, Mark Gales
- Date: 2026-06
- Venue: -
- Code: -
- Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning
- Author(s): Nuocheng Yang, Yechen He, Sihua Wang, Zihan Chen, Tony Q. S. Quek, Changchuan Yin
- Date: 2026-06
- Venue: -
- Code: -
- Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
- Author(s): Chenyu Zhou, Qiliang Jiang, Shuning Wu, Xu Zhou
- Date: 2026-06
- Venue: -
- Code: -
- PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning
- Author(s): Bo Su, Ankit Shah, Thai Le
- Date: 2026-06
- Venue: -
- Code: -
- SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
- Author(s): Jingyuan Zhang, Yucheng Bai, Peixi Wen, Zhehao Huang, Zhengbao He, Hanling Tian, Xinwen Cheng, Haiyin Ran, Xiaolin Huang
- Date: 2026-06
- Venue: -
- Code: -
- RepSelect: Robust LLM Unlearning via Representation Selectivity
- Author(s): Filip Sondej, Yushi Yang, Adam Mahdi
- Date: 2026-06
- Venue: -
- Code: -
- Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
- Author(s): Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou
- Date: 2026-06
- Venue: -
- Code: -
- Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning
- Author(s): Zirui Pang, Chenlong Zhang, Haosheng Tan, Zhuoran Jin, Jiaheng Wei, Zixin Zhong
- Date: 2026-06
- Venue: -
- Code: -
- Natively Unlearnable Large Language Models
- Author(s): Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan
- Date: 2026-06
- Venue: -
- Code: -
- TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
- Author(s): Zhengtao Yao, Liuyang Song, Hongbo Zhang, Chenhao Wei, Haoyan Xu, Guang Yang, Siheng Wang
- Date: 2026-06
- Venue: -
- Code: -
- MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
- Author(s): He Li, Haoang Chi, Qizhou Wang, Yunxin Mao, Zhiheng Zhang, Jie Tan, Tongliang Liu, Wenjing Yang, Bo Han
- Date: 2026-06
- Venue: -
- Code:
- Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
- Author(s): Bocheng Ju, Jianhua Wang, Chengliang Liu, Xiaolin Chang
- Date: 2026-06
- Venue: -
- Code: -
- Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models
- Author(s): Jingyi Xie, Yijun Lin, Yinjiang Xiong, Zhikun Zhang, Sai Li
- Date: 2026-06
- Venue: -
- Code: -
- SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
- Author(s): Zhijing Zhang, Jiaqi Ding, Qianshan Wei, Nan Zhou, Jiaqi Li, Yongliang Wu, Tongxin Zhu, Xiaolin Fang
- Date: 2026-06
- Venue: -
- Code: -
- TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
- Author(s): Ziheng Chen, Jiali Cheng, Zezhong Fan, Hadi Amiri, Diyuan Wu, Gabriele Tolomei, Yang Zhang
- Date: 2026-06
- Venue: -
- Code: -
- REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference
- Author(s): Anurag Sharma, Sai Teja Chunchu, Prasenjit Mitra, Sandipan Sikdar, Koustav Rudra
- Date: 2026-06
- Venue: -
- Code: -
- Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
- Author(s): Gizem Yüce, Giorgos Nikolaou, Nicolas Flammarion
- Date: 2026-06
- Venue: -
- Code: -
- Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
- Author(s): Lisa Bouger, Théo Lasnier, Philippe Loubet Moundi, Yannick Teglia, Djamé Seddah
- Date: 2026-06
- Venue: -
- Code: -
- Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
- Author(s): Clara Haya Suslik, Or Shafran, Mor Geva
- Date: 2026-06
- Venue: -
- Code: -
- Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
- Author(s): Chaoyi Xiang, Olga Ohrimenko, Benjamin I. P. Rubinstein, Lea Frermann
- Date: 2026-06
- Venue: -
- Code: -
- Fast Unlearning at Scale via Margin Self-Correction
- Author(s): Federico Di Gennaro, Alexander Shevchenko, Fanny Yang
- Date: 2026-06
- Venue: -
- Code: -
- Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
- Author(s): Junkai Chen, Yuhao He, Junxiang You, Ruiqi Liu, Chenyu Wang, Shu Wu
- Date: 2026-06
- Venue: -
- Code: -
- Break the Output Geometry for Large Language Model Unlearning
- Author(s): Yejin Kim, William F. Shen, Seokwon Jung, Seong Joon Oh
- Date: 2026-06
- Venue: ICML 2026 MemFM Workshop
- Code: -
- Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
- Author(s): Humzah Merchant, Bradford Levy
- Date: 2026-05
- Venue: -
- Code: -
- De-attribute to Forget for LLM Unlearning
- Author(s): Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim, See-Kiong Ng, Anthony Kum Hoe Tung, Bryan Kian Hsiang Low
- Date: 2026-05
- Venue: -
- Code: -
- AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis
- Author(s): Saeedeh Davoudi, Reihaneh Iranmanesh, Ophir Frieder, Nazli Goharian
- Date: 2026-05
- Venue: -
- Code: -
- ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
- Author(s): Ruihao Pan, Suhang Wang
- Date: 2026-05
- Venue: -
- Code: -
- On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
- Author(s): Xiaotian Ye, Xiaohan Wang, Mengqi Zhang, Shu Wu
- Date: 2026-05
- Venue: -
- Code: -
- On the Robustness of Machine Unlearning for Vision-Language Models
- Author(s): Yujie Lin, Kaidi Jia, Jiayao Ma, Chengyi Yang, Jinsong Su
- Date: 2026-05
- Venue: -
- Code:
- Model Unlearning Objectives Vary for Distinct Language Functions
- Author(s): Berk Atil, Vipul Gupta, Rebecca J. Passonneau
- Date: 2026-05
- Venue: -
- Code: -
- Measuring the Depth of LLM Unlearning via Activation Patching
- Author(s): Jaeung Lee, Dohyun Kim, Jaemin Jo
- Date: 2026-05
- Venue: -
- Code:
- DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
- Author(s): Xuyang Zhong, Qizhang Li, Yiwen Guo, Chen Liu
- Date: 2026-05
- Venue: -
- Code:
- Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models
- Author(s): Divyaksh Shukla, Ashutosh Modi
- Date: 2026-05
- Venue: -
- Code: -
- ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
- Author(s): Yujie Lin, Chengyi Yang, Zhishang Xiang, Yiping Song, Jinsong Su
- Date: 2026-05
- Venue: -
- Code:
- CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
- Author(s): Shen Lin, Junhao Dong, Rongjie Chen, Xiaoyu Zhang, Li Xu, Xiaofeng Chen
- Date: 2026-05
- Venue: -
- Code: -
- Machine Unlearning for Masked Diffusion Language Models
- Author(s): Georu Lee, Seungwon Jeong, Hoki Kim, Jinseong Park, Woojin Lee
- Date: 2026-05
- Venue: -
- Code:
- Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
- Author(s): Puning Yang, Junchi Yu, Qizhou Wang, Philip Torr, Bo Han, Xiuying Chen
- Date: 2026-05
- Venue: -
- Code:
- ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
- Author(s): Jiahui Guang, Yingjie Zhu, Cuiyun Gao, Haiyan Wang, Jing Li, Di Shao, Zhaoquan Gu
- Date: 2026-05
- Venue: -
- Code: -
- Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
- Author(s): Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
- Date: 2026-05
- Venue: -
- Code: -
- Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
- Author(s): Kyomin Hwang, Hyeonjin Kim, Sangyeon Cho, Nojun Kwak
- Date: 2026-05
- Venue: -
- Code: -
- ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
- Author(s): Shen Lin, Jing Lin, Junhao Dong, Piotr Koniusz, Li Xu
- Date: 2026-05
- Venue: -
- Code: -
- Inference-Time Machine Unlearning via Gated Activation Redirection
- Author(s): Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinskü
- Date: 2026-05
- Venue: -
- Code: -
- BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
- Author(s): Jagadeesh Rachapudi, Ritali Vatsi, Pranav Singh, Praful Hambarde, Amit Shukla
- Date: 2026-05
- Venue: -
- Code:
- Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
- Author(s): Zeguan Xiao, Xuanzhe Xu, Yun Chen, Yong Wang, Jian Yang, Yanqing Hu, Guanhua Chen
- Date: 2026-05
- Venue: -
- Code: -
- PPU-Bench: Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
- Author(s): Jiahui Guang, Zexun Zhan, Zhenlin Xu, Cuiyun Gao, Haiyan Wang, Jing Li, Zhaoquan Gu, Yanchun Zhang
- Date: 2026-05
- Venue: -
- Code: -
- Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
- Author(s): Renjie Gu, Jiazhen Du, Yihua Zhang, Sijia Liu
- Date: 2026-05
- Venue: -
- Code: -
- Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
- Author(s): Kaidi Jia, Yujie Lin, Chengyi Yang, Jiayao Ma, Jinsong Su
- Date: 2026-05
- Venue: -
- Code:
- SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
- Author(s): Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei, Mohammad Rostami, Jesse Thomason, Robin Jia
- Date: 2026-05
- Venue: -
- Code: -
- ICU-Bench: Benchmarking Continual Unlearning in Multimodal Large Language Models
- Author(s): Yuhang Wang, Wenjie Mei, Junkai Zhang, Guangyu He, Zhenxing Niu, Haichang Gao
- Date: 2026-05
- Venue: -
- Code: -
- Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
- Author(s): Yuhang Wang, Zhenxing Niu, Haoxuan Ji, Guangyu He, Linlin Zhang, Haichang Gao
- Date: 2026-05
- Venue: -
- Code: -
- MidSteer: Optimal Affine Framework for Steering Generative Models
- Author(s): Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu, Martin Benning, Gregory Slabaugh, Jiankang Deng, Ismail Elezi
- Date: 2026-05
- Venue: -
- Code: -
- Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models
- Author(s): Quintin Pope, Ajay Hayagreeve Balaji, Jacques Thibodeau, Xiaoli Fern
- Date: 2026-05
- Venue: -
- Code: -
- Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
- Author(s): JuneHyoung Kwon, MiHyeon Kim, Eunju Lee, JungMin Yun, Byeonggeuk Lim, YoungBin Kim
- Date: 2026-05
- Venue: ACL 2026 Findings
- Code: -
- Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
- Author(s): JuneHyoung Kwon, JungMin Yun, YoungBin Kim
- Date: 2026-05
- Venue: LREC 2026
- Code: -
- Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score
- Author(s): Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel
- Date: 2026-05
- Venue: -
- Code:
- DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
- Author(s): Abdullah Ahmad Khan, Ferdous Sohel
- Date: 2026-05
- Venue: -
- Code: -
- Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
- Author(s): Chenchen Tan, Xinghao Li, Shujie Cui, Youyang Qu, Cunjian Chen, Longxiang Gao
- Date: 2026-05
- Venue: -
- Code: -
- Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
- Author(s): Anamika Paul Rupa, Anietie Andy
- Date: 2026-05
- Venue: -
- Code: -
- LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
- Author(s): Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar, Murtuza Jadliwala
- Date: 2026-05
- Venue: -
- Code: -
- Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
- Author(s): Jiawei Wu, Doudou Zhou
- Date: 2026-05
- Venue: -
- Code: -
- When Forgetting Reveals: Black-Box Inversion Attacks on Unlearning in Large Language Models
- Author(s): Zijun Zhang, Bang Wu, Xingliang Yuan
- Date: 2026-05
- Venue: ESORICS 2025 International Workshops
- Code: -
- DynaUnlearn: Continual Adversarial Unlearning for Robust Safety in LLM Agents
- Author(s): Nina Xie, Xinyu Deng
- Date: 2026-05
- Venue: ESORICS 2025 International Workshops
- Code: -
- Unlearning by Construction: Auxiliary Prediction as a Path to LLM Unlearning
- Author(s): Jiabao Ji, Yujian Liu, Shiyu Chang
- Date: 2026-05
- Venue: -
- Code: -
- UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks
- Author(s): Tianlong Yu, Yang Yang, Xiao Luo, Lihong Liu, Fudu Xing, Zui Tao, Kailong Wang, Gaoyang Liu, Ting Bi
- Date: 2026-04
- Venue: -
- Code: -
- PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
- Author(s): Xiaoyi Chen, Haoyuan Wang, Siyuan Tang, Sijia Liu, Liya Su, XiaoFeng Wang, Haixu Tang
- Date: 2026-04
- Venue: -
- Code: -
- CAP: Controllable Alignment Prompting for Unlearning in LLMs
- Author(s): Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian
- Date: 2026-04
- Venue: ACL 2026
- Code: -
- Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
- Author(s): Seunghee Koh, Sunghyun Baek, Youngdong Kim, Junmo Kim
- Date: 2026-04
- Venue: ACL 2026
- Code: -
- Representation-Guided Parameter-Efficient LLM Unlearning
- Author(s): Zeguan Xiao, Lang Mo, Yun Chen, Lei Yang, Jiehui Zhao, Lili Yang, Guanhua Chen
- Date: 2026-04
- Venue: -
- Code: -
- Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
- Author(s): Ziwen Liu, Huawei Lin, Yide Ran, Denghui Zhang, Jianwen Xie, Chuan Li, Weijie Zhao, Zhaozhuo Xu
- Date: 2026-04
- Venue: -
- Code: -
- CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
- Author(s): Junyi Li, Yongqiang Chen, Ningning Ding
- Date: 2026-04
- Venue: ACL 2026
- Code: -
- Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
- Author(s): Yisheng Zhong, Sijia Liu, Zhuangdi Zhu
- Date: 2026-04
- Venue: -
- Code: -
- Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
- Author(s): Zeguan Xiao, Siqing Li, Yong Wang, Xuetao Wei, Jian Yang, Yun Chen, Guanhua Chen
- Date: 2026-04
- Venue: ACL 2026
- Code: -
- CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
- Author(s): Seyun Bae, Seokhan Lee, Eunho Yang
- Date: 2026-04
- Venue: ACL 2026 Findings
- Code: -
- CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
- Author(s): Yian Wang, Yuen Chen, Agam Goyal, Hari Sundaram
- Date: 2026-04
- Venue: -
- Code: -
- From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
- Author(s): Wenxuan Li, Zhenfei Zhang, Mi Zhang, Geng Hong, Mi Wen, Xiaoyu You, Min Yang
- Date: 2026-04
- Venue: -
- Code: -
- WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework
- Author(s): Xingjian Zhao, Mohammad Mohammadi Amiri, Malik Magdon-Ismail
- Date: 2026-04
- Venue: -
- Code: -
- RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair
- Author(s): Jagadeesh Rachapudi, Pranav Singh, Ritali Vatsi, Praful Hambarde, Amit Shukla
- Date: 2026-04
- Venue: -
- Code: -
- Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments
- Author(s): Esen Kurt, Haithem Afli
- Date: 2026-04
- Venue: PoliticalNLP 2026
- Code: -
- Mitigating Privacy Risk via Forget Set-Free Unlearning
- Author(s): Aviraj Newatia, Michael Cooper, Viet Nguyen, Rahul G. Krishnan
- Date: 2026-04
- Venue: -
- Code: -
- Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
- Author(s): Eric Easley, Sebastian Farquhar
- Date: 2026-04
- Venue: -
- Code: -
- Exclusive Unlearning
- Author(s): Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao, Yohei Oseki, Masaru Isonuma
- Date: 2026-04
- Venue: -
- Code: -
- Can Large Language Models Reinvent Foundational Algorithms?
- Author(s): Jian Zhao, Haoren Luo, Yu Wang, Yuhan Cao, Pingyue Sheng, Tianxing He
- Date: 2026-04
- Venue: -
- Code: -
- CURE:Circuit-Aware Unlearning for LLM-based Recommendation
- Author(s): Ziheng Chen, Jiali Cheng, Zezhong Fan, Hadi Amiri, Yunzhi Yao, Xiangguo Sun, Yang Zhang
- Date: 2026-04
- Venue: -
- Code: -
- Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning
- Author(s): Aobo Chen, Chenxu Zhao, Chenglin Miao, Mengdi Huai
- Date: 2026-04
- Venue: -
- Code: -
- Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
- Author(s): Yancheng Huang, Changsheng Wang, Chongyu Fan, Yicheng Lang, Bingqi Shang, Yang Zhang, Mingyi Hong, Qing Qu, Alvaro Velasquez, Sijia Liu
- Date: 2026-04
- Venue: -
- Code:
- VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
- Author(s): Ravi Ranjan, Agoritsa Polyzou
- Date: 2026-04
- Venue: -
- Code: -
- Selective Forgetting for Large Reasoning Models
- Author(s): Tuan Le, Wei Qian, Mengdi Huai
- Date: 2026-04
- Venue: -
- Code: -
- Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
- Author(s): Zhangyun Tan, Zeliang Zhang, Susan Liang, Yolo Yunlong Tang, Lisha Chen, Chenliang Xu
- Date: 2026-04
- Venue: -
- Code:
- Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
- Author(s): Dayong Ye, Tainqing Zhu, Congcong Zhu, Feng He, Qi He, Shang Wang, Bo Liu, Wanlei Zhou
- Date: 2026-04
- Venue: -
- Code: -
- Unlearning-induced Collateral Corruption in Machine Unlearning for LLMs
- Author(s): Bo Su, Yueru Yan, Thai Le
- Date: 2026-04
- Venue: MSLD 2026
- Code: -
- Towards Practical LLM Unlearning: Efficient, Modular, and Retain-Free
- Author(s): Peng Liu, Peng-Fei Zhang, Jianfeng Qu, Ximing Li, Zhixu Li, Pengpeng Zhao
- Date: 2026-04
- Venue: WWW 2026
- Code: -
- Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models
- Author(s): Jiajia Song, Zhihan Guo, Jionghao Lin
- Date: 2026-03
- Venue: -
- Code: -
- Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
- Author(s): Hyundong Jin, Dongyoon Han, Eunwoo Kim
- Date: 2026-03
- Venue: -
- Code: -
- Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning
- Author(s): Iyad Ait Hou, Shrenik Borad, Harsh Sharma, Pooja Srinivasan, Rebecca Hwa, Aya Zirikly
- Date: 2026-03
- Venue: -
- Code: -
- RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
- Author(s): Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou
- Date: 2026-03
- Venue: -
- Code: -
- Relationship-Aware Safety Unlearning for Multimodal LLMs
- Author(s): Vishnu Narayanan Anilkumar, Abhijith Sreesylesh Babu, Trieu Hai Vo, Mohankrishna Kolla, Alexander Cuneo
- Date: 2026-03
- Venue: -
- Code: -
- GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
- Author(s): Chahana Dahal, Ashutosh Balasubramaniam, Zuobin Xiong
- Date: 2026-03
- Venue: -
- Code: -
- The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
- Author(s): Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan, Nathalie Baracaldo, Diyi Yang
- Date: 2026-03
- Venue: -
- Code: -
- Explainable LLM Unlearning Through Reasoning
- Author(s): Junfeng Liao, Qizhou Wang, Shanshan Ye, Xin Yu, Ling Chen, Zhen Fang
- Date: 2026-03
- Venue: -
- Code: -
- ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
- Author(s): Xunlei Chen, Jinyu Guo, Yuang Li, Zhaokun Wang, Yi Gong, Jie Zou, Jiwei Wei, Wenhong Tian
- Date: 2026-03
- Venue: -
- Code: -
- Attention Smoothing Is All You Need For Unlearning
- Author(s): Saleh Zare Zade, Xiangyu Zhou, Sijia Liu, Dongxiao Zhu
- Date: 2026-03
- Venue: -
- Code: -
- A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction
- Author(s): Ruihao Pan, Suhang Wang
- Date: 2026-03
- Venue: -
- Code: -
- ROKA: Robust Knowledge Unlearning against Adversaries
- Author(s): Jinmyeong Shin, Joshua Tapia, Nicholas Ferreira, Gabriel Diaz, Moayed Daneshyari, Hyeran Jeon
- Date: 2026-03
- Venue: -
- Code: -
- Learn to be Unlearned: Optimizing Language Models for Unlearning via Clustered Gradient Routing
- Author(s): Vincent Hanke, Jing Xu, Martin Pawelczyk, Michael Backes, Adam Dziedzic, Franziska Boenisch
- Date: 2026-03
- Venue: ICLR 2026 Workshop Trustworthy AI
- Code: -
- From Chaos to Clarity: A Knowledge Graph-Driven Audit Dataset Generation Framework for LLM Unlearning
- Author(s): Weipeng Jiang, Juan Zhai, Shiqing Ma, Ziyan Lei, Xiaofei Xie, Yige Wang, Chao Shen
- Date: 2026-03
- Venue: AAAI 2026
- Code:
- A Robust Unlearning Method with Adaptive Knowledge Guidance and Memory Preservation
- Author(s): Jingyuan Tian, Xiaofei Zhou
- Date: 2026-03
- Venue: AAAI 2026
- Code: -
- TUNE: A Task For Turkish Machine Unlearning For Data Privacy
- Author(s): Doruk Benli, Ada Canoğlu, Nehir İlkim Gönençer, Dilara Keküllüoğlu
- Date: 2026-03
- Venue: SIGTURK 2026
- Code: -
- MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
- Author(s): Tiantong Wang, Xinyu Yan, Tiantong Wu, Yurong Hao, Yong Jiang, Fei Huang, Wei Yang Bryan Lim
- Date: 2026-02
- Venue: -
- Code:
- U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation
- Author(s): Zezheng Wu, Rui Wang, Xinghe Cheng, Yang Shao, Qing Yang, Jiapu Wang, Jingwei Zhang
- Date: 2026-02
- Venue: -
- Code: -
- Layer-Targeted Multilingual Knowledge Erasure in Large Language Models
- Author(s): Taoran Li, Varun Chandrasekaran, Zhiyuan Yu
- Date: 2026-02
- Venue: -
- Code: -
- Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
- Author(s): Borisiuk Anna, Andrey Savchenko, Alexander Panchenko, Elena Tutubalina
- Date: 2026-02
- Venue: -
- Code: -
- KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models
- Author(s): Ce Fang, Zhikun Zhang, Min Chen, Qing Liu, Lu Zhou, Zhe Liu, Yunjun Gao
- Date: 2026-02
- Venue: -
- Code: -
- Agentic Unlearning: When LLM Agent Meets Machine Unlearning
- Author(s): Bin Wang, Fan Wang, Pingping Wang, Jinyu Cong, Yang Yu, Yilong Yin, Zhongyi Han, Benzheng Wei
- Date: 2026-02
- Venue: -
- Code: -
- MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
- Author(s): Haoyu Wang, Zhuo Huang, Xiaolong Wang, Bo Han, Zhiwei Lin, Tongliang Liu
- Date: 2026-02
- Venue: -
- Code: -
- Quantization-Robust LLM Unlearning via Low-Rank Adaptation
- Author(s): João Vitor Boer Abitante, Joana Meneguzzo Pasquali, Luan Fonseca Garcia, Ewerton de Oliveira, Thomas da Silva Paula, Rodrigo C. Barros, Lucas S. Kupssinskü
- Date: 2026-02
- Venue: -
- Code: -
- Gauss-Newton Unlearning for the LLM Era
- Author(s): Lev McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei, Nicolas Papernot, Sheila A. McIlraith, Roger Grosse
- Date: 2026-02
- Venue: -
- Code: -
- REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop
- Author(s): Patryk Rybak, Paweł Batorski, Paul Swoboda, Przemysław Spurek
- Date: 2026-02
- Venue: -
- Code:
- Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks
- Author(s): Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi Ma, Yun Huang, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang
- Date: 2026-02
- Venue: -
- Code: -
- CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
- Author(s): Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu
- Date: 2026-02
- Venue: -
- Code: -
- AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
- Author(s): Pengyu Li, Lingling Zhang, Zhitao Gao, Yanrui Wu, Yuxuan Dong, Huan Liu, Bifan Wei, Jun Liu
- Date: 2026-02
- Venue: -
- Code:
- Sparsity-Aware Unlearning for Large Language Models
- Author(s): Yuze Wang, Yujia Tong, Ke Xu, Jingling Yuan, Jiawei Jiang, Chuang Hu
- Date: 2026-01
- Venue: -
- Code: -
- Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data
- Author(s): Eugenia Iofinova, Dan Alistarh
- Date: 2026-01
- Venue: -
- Code:
- Per-parameter Task Arithmetic for Unlearning in Large Language Models
- Author(s): Chengyi Cai, Zesheng Ye, Jiangchao Yao, Jianzhong Qi, Bo Han, Xiaolu Zhang, Feng Liu, Jun Zhou
- Date: 2026-01
- Venue: -
- Code: -
- From Logits to Latents: Contrastive Representation Shaping for LLM Unlearning
- Author(s): Haoran Tang, Rajiv Khanna
- Date: 2026-01
- Venue: -
- Code: -
- Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning
- Author(s): Chengyi Cai, Zesheng Ye, Peike Li, Bo Han, Jianzhong Qi, Feng Liu
- Date: 2026-01
- Venue: -
- Code: -
- Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models
- Author(s): Yejin Kim, Dongjun Hwang, Sungmin Cha, Junsuk Choe
- Date: 2026-01
- Venue: -
- Code: -
- Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities
- Author(s): Tien Dang, The-Hai Nguyen, Dinh Mai Phuong, Nguyen Minh Phuong, Hoang Thanh-Tung, Le-Minh Nguyen, Naoya Inoue
- Date: 2026-01
- Venue: -
- Code: -
- FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning
- Author(s): Xiaoyu Xu, Minxin Du, Kun Fang, Zi Liang, Yaxin Xiao, Zhicong Huang, Cheng Hong, Qingqing Ye, Haibo Hu
- Date: 2026-01
- Venue: -
- Code: -
- DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher
- Author(s): Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu
- Date: 2026-01
- Venue: -
- Code: -
- Reinforcement Unlearning via Group Relative Policy Optimization
- Author(s): Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci
- Date: 2026-01
- Venue: ICLR 2026
- Code: -
- LLMs Can Unlearn Refusal with Only 1,000 Benign Samples
- Author(s): Yangyang Guo, Ziwei Xu, Si Liu, Zhiming Zheng, Mohan Kankanhalli
- Date: 2026-01
- Venue: -
- Code:
- Towards Fair Large Language Model-based Recommender Systems without Costly Retraining
- Author(s): Jin Li, Huilin Gu, Shoujin Wang, Qi Zhang, Shui Yu, Chen Wang, Xiwei Xu, Fang Chen
- Date: 2026-01
- Venue: WWW 2026
- Code:
- Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
- Author(s): Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer, Daniel Rueckert
- Date: 2026-01
- Venue: -
- Code: -
- GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
- Author(s): Andy Zhu, Rongzhe Wei, Yupu Gu, Pan Li
- Date: 2026-01
- Venue: -
- Code: -
- Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
- Author(s): Xianya Fang, Feiyang Ren, Xiang Chen, Yu Tian, Zhen Bi, Haiyang Yu, Sheng-Jun Huang
- Date: 2026-01
- Venue: -
- Code: -
- Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
- Author(s): Xinjie Zhou, Zhihui Yang, Lechao Cheng, Sai Wu, Gang Chen
- Date: 2026-01
- Venue: -
- Code: -
- QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs
- Author(s): Himanshu Mishra, Kanwal Mehreen
- Date: 2026-01
- Venue: -
- Code: -
- Auditing Language Model Unlearning via Information Decomposition
- Author(s): Anmol Goel, Alan Ritter, Iryna Gurevych
- Date: 2026-01
- Venue: EACL 2026
- Code: -
- Representation-Aware Unlearning via Activation Signatures: From Suppression to Knowledge-Signature Erasure
- Author(s): Syed Naveed Mahmood, Md. Rezaur Rahman Bhuiyan, Tasfia Zaman, Jareen Tasneem Khondaker, Md. Sameer Sakib, K. M. Shadman Wadith, Nazia Tasnim, Farig Sadeque
- Date: 2026-01
- Venue: -
- Code: -
- Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric
- Author(s): Jiali Cheng, Ziheng Chen, Chirag Agarwal, Hadi Amiri
- Date: 2026-01
- Venue: -
- Code: -
- STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models
- Author(s): Jingjing Zhou, Gaoxiang Cong, Li Su, Liang Li
- Date: 2026-01
- Venue: -
- Code: -
- BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
- Author(s): Pengyang Shao, Naixin Zhai, Lei Chen, Yonghui Yang, Fengbin Zhu, Xun Yang, Meng Wang
- Date: 2026-01
- Venue: -
- Code: -
- Consistency-Aware Editing for Entity-level Unlearning in Language Models
- Author(s): Xiaoqi Han, Víctor Gutiérrez-Basulto, Ru Li, Xiaoli Li, Jiye Liang, Jeff Z. Pan
- Date: 2026-01
- Venue: -
- Code: -
- ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models
- Author(s): Zhenhua Xu, Haobo Zhang, Zhebo Wang, Qichen Liu, Haitao Xu, Wenpeng Xing, Meng Han
- Date: 2026-01
- Venue: ICASSP 2026
- Code:
- Forgetting Similar Samples: Can Machine Unlearning Do it Better?
- Author(s): Heng Xu, Tianqing Zhu, Dayong Ye, Lefeng Zhang, Le Wang, Wanlei Zhou
- Date: 2026-01
- Venue: -
- Code: -
- Evaluating Cross-Lingual Unlearning in Multilingual Language Models
- Author(s): Tyler Lizzo, Larry Heck
- Date: 2026-01
- Venue: -
- Code: -
- Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs
- Author(s): Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi
- Date: 2026-01
- Venue: -
- Code: -
- From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
- Author(s): Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Shiyu Zhang, Peizhao Hu, Qingqing Ye, Haibo Hu
- Date: 2026-01
- Venue: -
- Code: -
- Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs
- Author(s): Dinesh Srivasthav P, Ashok Urlana, Rahul Mishra, Bala Mallikarjunarao Garlapati, Ponnurangam Kumaraguru
- Date: 2026-01
- Venue: -
- Code: -
- Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
- Author(s): Naixin Zhai, Pengyang Shao, Binbin Zheng, Yonghui Yang, Fei Shen, Long Bai, Xun Yang
- Date: 2026-01
- Venue: -
- Code: -
- JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
- Author(s): Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Zhaoye Li, Bin Ji, Baosheng Wang, Jie Yu
- Date: 2026-01
- Venue: -
- Code: -
- UnPII: Unlearning Personally Identifiable Information with Quantifiable Exposure Risk
- Author(s): Intae Jeon, Yujeong Kwon, Hyungjoon Koo
- Date: 2026-01
- Venue: -
- Code: -
- Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models
- Author(s): Jiaqi Li, Zihan You, Ruoyan Shen, Shenyu Zhang, Songlin Zhai, Yongrui Chen, Chuanyi Zhang, Jiahui Geng, Fakhri Karray, Sheng Bi, Guilin Qi
- Date: 2026-01
- Venue: ICLR 2026
- Code: -
- Robust LLM Unlearning via Post Judgment and Multi-round Thinking
- Author(s): Xinrui Chen, Xu Cao, Jianhao Zhang, Pinlong Zhao, Di Gao, Ou Wu
- Date: 2026-01
- Venue: ICLR 2026
- Code:
- DAWI: Dual Anchored Weighted Interpolation for LLM Unlearning
- Author(s): Jonathan Zhou
- Date: 2026-01
- Venue: ICLR 2026
- Code: -
- Explicit Representation Alignment via Subspace Elimination for Robust LLM Unlearning
- Author(s): Keonwoo Kim, Hyowon Cho, Sungwon Chae, Sangwon Yoon, Min Choi, Hoki Kim
- Date: 2026-01
- Venue: ICLR 2026
- Code: -
- Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs
- Author(s): Xin Gao, Ruiyi Zhang, Daniel Du, Saurabh Mahindre, Sai Ashish Somayajula, Pengtao Xie
- Date: 2025-10
- Venue: -
- Code:
2025
- UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation
- Author(s): Chengye Wang, Yuyuan Li, XiaoHua Feng, Chaochao Chen, Xiaolin Zheng, Jianwei Yin
- Date: 2025-12
- Venue: NeurIPS 2025
- Code:
- Elastic Robust Unlearning of Specific Knowledge in Large Language Models
- Author(s): Yize Sui, Jing Ren, Wenjing Yang, Ruochun Jin, Liyang Xu, Xiyao Liu, Ji Wang
- Date: 2025-12
- Venue: NeurIPS 2025
- Code: -
- MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs
- Author(s): Shubhadip Nag, Srinjoy Das, Agniva Saha, Anushree Ghosh, Soumi Das, Tarun Kumar, Suparna Bhattacharya, Sourangshu Bhattacharya
- Date: 2025-12
- Venue: NeurIPS 2025 Reliable ML Workshop
- Code: -
- Identifying Unlearned Data in LLMs via Membership Inference Attacks
- Author(s): Advit Deepak, Megan Mou, Jing Huang, Diyi Yang
- Date: 2025-11
- Venue: EMNLP 2025
- Code:
- Unlearners Can Lie: Evaluating "Honesty" in LLM Unlearning
- Author(s): Renjie Gu, Jiazhen Du, Yihua Zhang, Sijia Liu
- Date: 2025-10
- Venue: NeurIPS 2025 Lock-LLM Workshop
- Code: -
- The Role of Learning and Memorization in Relabeling-based Unlearning for LLMs
- Author(s): Xinyu Zhou, Pushen Wang, Ehsan Saleh, Raef Bassily, Jia Liu
- Date: 2025-09
- Venue: -
- Code: -
- On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
- Author(s): Jianing Zhu, Zongze Li, Chandler Squires, Qizhou Wang, Bo Han, Pradeep Ravikumar
- Date: 2025-09
- Venue: -
- Code: -
- Lifelong Unlearning for Multimodal Large Language Models
- Author(s): He Li, Haoang Chi, Qizhou Wang, Yunxin Mao, Jie Tan, Tongliang Liu, Wenjing Yang, Bo Han
- Date: 2025-09
- Venue: -
- Code: -
- MOUCHI: Mitigating Over-forgetting in Unlearning Copyrighted Information
- Author(s): Irfan Akbar, Dongmin Park, Patara Trirat, Jae-Gil Lee
- Date: 2025-09
- Venue: -
- Code: -
- Provably Continual Unlearning for Large Language Model
- Author(s): Haoran Shi, Hao Zhu, Han Yu, Lizhen Cui, Yifei Zhang, Piotr Koniusz
- Date: 2025-09
- Venue: -
- Code: -
- SELU: Energy-based Targeted Unlearning in LLMs
- Author(s): Passawis Chaiyapattanaporn, Pontus Stenetorp, Yihong Chen
- Date: 2025-09
- Venue: -
- Code: -
- POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Fine-tuning and Prompt-based Attacks
- Author(s): Zhangheng Li, Junyuan Hong, Jianing Zhu, Sungmin Eum, Shuowen Hu, Suya You, Zhangyang Wang
- Date: 2025-09
- Venue: -
- Code: -
- Refusal Is Not an Option: Unlearning Safety Alignment of Large Language Models
- Author(s): Minkyoo Song, Hanna Kim, Jaehan Kim, Seungwon Shin, Sooel Son
- Date: 2025-08
- Venue: USENIX Security 2025
- Code:
- Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models
- Author(s): Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi
- Date: 2025-07
- Venue: ACL 2025 Findings
- Code: -
- Rethinking Unlearning for Large Reasoning Models
- Author(s): Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
- Date: 2025-06
- Venue: ICML 2025 Workshop on Machine Unlearning for Generative AI
- Code: -
- Unlearning in Large Language Models: We Are Not There Yet
- Author(s): Alberto Blanco-Justicia, Josep Domingo-Ferrer, Najeeb Moharram Jebreel, Benet Manzanares-Salor, David Sanchez
- Date: 2025-01
- Venue: IEEE Computer 2025
- Code: -
- Investigating Model Editing for Unlearning in Large Language Models
- Author(s): Shariqah Hossain, Lalana Kagal
- Date: 2025-12
- Venue: -
- Code: -
- The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation
- Author(s): Hengrui Jia, Taoran Li, Jonas Guan, Varun Chandrasekaran
- Date: 2025-12
- Venue: -
- Code: -
- Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
- Author(s): Wei Qian, Chenxu Zhao, Yangyi Li, Mengdi Huai
- Date: 2025-12
- Venue: -
- Code: -
- Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
- Author(s): Hongji Li, Junchi Yao, Manjiang Yu, Priyanka Singh, Xue Li, Di Wang, Lijie Hu
- Date: 2025-12
- Venue: -
- Code: -
- Feature-Selective Representation Misdirection for Machine Unlearning
- Author(s): Taozhao Chen, Linghan Huang, Kim-Kwang Raymond Choo, Huaming Chen
- Date: 2025-12
- Venue: -
- Code: -
- FAME: Fictional Actors for Multilingual Erasure
- Author(s): Claudio Savelli, Moreno La Quatra, Alkis Koudounas, Flavio Giobergia
- Date: 2025-12
- Venue: -
- Code: -
- Explainable reinforcement learning from human feedback to improve alignment
- Author(s): Shicheng Liu, Siyuan Xu, Wenjie Qiu, Hangfan Zhang, Minghui Zhu
- Date: 2025-12
- Venue: -
- Code: -
- FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
- Author(s): Si Qi Goh, Yongsen Zheng, Ziyao Liu, Sami Hormi, Kwok-Yan Lam
- Date: 2025-12
- Venue: -
- Code: -
- MLLM Machine Unlearning via Visual Knowledge Distillation
- Author(s): Yuhang Wang, Zhenxing Niu, Haoxuan Ji, Guangyu He, Haichang Gao, Gang Hua
- Date: 2025-12
- Venue: -
- Code: -
- MedForget: Hierarchy-Aware Multimodal Unlearning Testbed for Medical AI
- Author(s): Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal
- Date: 2025-12
- Venue: -
- Code: -
- LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples
- Author(s): Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani
- Date: 2025-12
- Venue: -
- Code: -
- Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
- Author(s): Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani
- Date: 2025-12
- Venue: -
- Code: -
- Delete and Retain: Efficient Unlearning for Document Classification
- Author(s): Aadya Goel, Mayuri Sridhar
- Date: 2025-12
- Venue: -
- Code: -
- Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
- Author(s): Igor Shilov, Alex Cloud, Aryo Pradipta Gema, Jacob Goldman-Wetzler, Nina Panickssery, Henry Sleight, Erik Jones, Cem Anil
- Date: 2025-12
- Venue: -
- Code: -
- When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation
- Author(s): Yiwen Liang, Qiufeng Li, Shikai Wang, Weidong Cao
- Date: 2025-12
- Venue: -
- Code: -
- RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
- Author(s): Guoshenghui Zhao, Huawei Lin, Weijie Zhao
- Date: 2025-12
- Venue: -
- Code: -
- RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
- Author(s): Roy Rinberg, Usha Bhalla, Igor Shilov, Flavio P. Calmon, Rohit Gandikota
- Date: 2025-12
- Venue: -
- Code: -
- Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
- Author(s): Zhen Zeng, Leijiang Gu, Zhangling Duan, Feng Li, Zenglin Shi, Cees G. M. Snoek, Meng Wang
- Date: 2025-11
- Venue: -
- Code: -
- Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
- Author(s): Yi Zhang, Tianxiang Xu, Zijian Li, Chao Zhang, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, Bing Chen
- Date: 2025-11
- Venue: -
- Code: -
- SineProject: Machine Unlearning for Stable Vision Language Alignment
- Author(s): Arpit Garg, Hemanth Saratchandran, Simon Lucey
- Date: 2025-11
- Venue: -
- Code: -
- Geometric-disentangelment Unlearning
- Author(s): Duo Zhou, Yuji Zhang, Tianxin Wei, Ruizhong Qiu, Ke Yang, Xiao Lin, Cheng Qian, Jingrui He, Hanghang Tong, Chengxiang Zhai, Heng Ji, Huan Zhang
- Date: 2025-11
- Venue: -
- Code:
- From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
- Author(s): Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, Sattvik Sahai, Prasoon Goyal, Kai-Wei Chang, Tao Zhang, Rahul Gupta
- Date: 2025-11
- Venue: -
- Code: -
- Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
- Author(s): Shizhou Xu, Yuan Ni, Stefan Broecker, Thomas Strohmer
- Date: 2025-11
- Venue: -
- Code: -
- AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
- Author(s): Haokun Chen, Jianing Li, Yao Zhang, Jinhe Bi, Yan Xia, Jindong Gu, Volker Tresp
- Date: 2025-11
- Venue: -
- Code: -
- Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
- Author(s): James Jin Kang, Dang Bui, Thanh Pham, Huo-Chong Ling
- Date: 2025-11
- Venue: -
- Code: -
- Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion
- Author(s): Feng Guo, Yuntao Wen, Shen Gao, Junshuo Zhang, Shuo Shang
- Date: 2025-11
- Venue: -
- Code: -
- Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
- Author(s): Kunhao Li, Wenhao Li, Di Wu, Lei Yang, Jun Bai, Ju Jia, Jason Xue
- Date: 2025-11
- Venue: -
- Code: -
- DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
- Author(s): Yaxuan Wang, Chris Yuhao Liu, Quan Liu, Jinglong Pang, Wei Wei, Yujia Bao, Yang Liu
- Date: 2025-11
- Venue: -
- Code: -
- Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
- Author(s): Hadi Reisizadeh, Jiajun Ruan, Yiwei Chen, Soumyadeep Pal, Sijia Liu, Mingyi Hong
- Date: 2025-11
- Venue: -
- Code: -
- REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs
- Author(s): Liran Cohen, Yaniv Nemcovesky, Avi Mendelson
- Date: 2025-11
- Venue: -
- Code: -
- The Realignment Problem: When Right becomes Wrong in LLMs
- Author(s): Aakash Sen Sharma, Debdeep Sanyal, Vivek Srivastava, Shirish Karande, Murari Mandal
- Date: 2025-11
- Venue: -
- Code: -
- The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework
- Author(s): Aakriti Shah, Thai Le
- Date: 2025-10
- Venue: -
- Code: -
- From Memorization to Reasoning in the Spectrum of Loss Curvature
- Author(s): Jack Merullo, Srihita Vatsavaya, Lucius Bushnaq, Owen Lewis
- Date: 2025-10
- Venue: -
- Code: -
- Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
- Author(s): Kyomin Hwang, Hyeonjin Kim, Seungyeon Kim, Sunghyun Wee, Nojun Kwak
- Date: 2025-10
- Venue: -
- Code: -
- Probing Knowledge Holes in Unlearned LLMs
- Author(s): Myeongseob Ko, Hoang Anh Just, Charles Fleming, Ming Jin, Ruoxi Jia
- Date: 2025-10
- Venue: -
- Code: -
- The Evaluation of Retrieval-Based Unlearning Mechanisms on Large Language Models
- Author(s): Zihan Xie, Lefeng Zhang, Minfeng Qi
- Date: 2025-11
- Venue: KSEM 2025
- Code: -
- OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
- Author(s): Hao Zheng, Zirui Pang, Ling li, Zhijie Deng, Yuhan Pu, Zhaowei Zhu, Xiaobo Xia, Jiaheng Wei
- Date: 2025-10
- Venue: -
- Code: -
- Label Smoothing Improves Gradient Ascent in LLM Unlearning
- Author(s): Zirui Pang, Hao Zheng, Zhijie Deng, Ling Li, Zixin Zhong, Jiaheng Wei
- Date: 2025-10
- Venue: -
- Code: -
- Leverage Unlearning to Sanitize LLMs
- Author(s): Antoine Boutet, Lucas Magnana
- Date: 2025-10
- Venue: -
- Code: -
- Hubble: a Model Suite to Advance the Study of LLM Memorization
- Author(s): Johnny Tian-Zheng Wei, Ameya Godbole, Mohammad Aflah Khan, Ryan Wang, Xiaoyuan Zhu, James Flemings, Nitya Kashyap, Krishna P. Gummadi, Willie Neiswanger, Robin Jia
- Date: 2025-10
- Venue: -
- Code: -
- LLM Unlearning with LLM Beliefs
- Author(s): Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu, Bo Han, Jiantao Zhou
- Date: 2025-10
- Venue: -
- Code: -
- Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
- Author(s): Yuefeng Peng, Parnian Afshar, Megan Ganji, Thomas Butler, Amir Houmansadr, Mingxian Wang, Dezhi Hong
- Date: 2025-10
- Venue: -
- Code: -
- Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
- Author(s): Chenchen Tan, Youyang Qu, Xinghao Li, Hui Zhang, Shujie Cui, Cunjian Chen, Longxiang Gao
- Date: 2025-10
- Venue: -
- Code: -
- Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
- Author(s): Bingqi Shang, Yiwei Chen, Yihua Zhang, Bingquan Shen, Sijia Liu
- Date: 2025-10
- Venue: -
- Code: -
- Hierarchical Federated Unlearning for Large Language Models
- Author(s): Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu
- Date: 2025-10
- Venue: -
- Code: -
- On the Impossibility of Retrain Equivalence in Machine Unlearning
- Author(s): Jiatong Yu, Yinghui He, Anirudh Goyal, Sanjeev Arora
- Date: 2025-10
- Venue: -
- Code: -
- Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
- Author(s): Sungjun Cho, Dasol Hwang, Frederic Sala, Sangheum Hwang, Kyunghyun Cho, Sungmin Cha
- Date: 2025-10
- Venue: -
- Code: -
- LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
- Author(s): Changsheng Wang, Yihua Zhang, Dennis Wei, Jinghan Jia, Pin-Yu Chen, Sijia Liu
- Date: 2025-10
- Venue: -
- Code: -
- Approximate Domain Unlearning for Vision-Language Models
- Author(s): Kodai Kawamura, Yuta Goto, Rintaro Yanagi, Hirokatsu Kataoka, Go Irie
- Date: 2025-10
- Venue: -
- Code: -
- SIMU: Selective Influence Machine Unlearning
- Author(s): Anu Agarwal, Mihir Pamnani, Dilek Hakkani-Tur
- Date: 2025-10
- Venue: -
- Code: -
- LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
- Author(s): Chongyu Fan, Changsheng Wang, Yancheng Huang, Soumyadeep Pal, Sijia Liu
- Date: 2025-10
- Venue: -
- Code: -
- Cross-Modal Attention Guided Unlearning in Vision-Language Models
- Author(s): Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van, Xintao Wu
- Date: 2025-10
- Venue: -
- Code: -
- (Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs
- Author(s): Jiashu Tao, Reza Shokri
- Date: 2025-10
- Venue: -
- Code: -
- Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
- Author(s): Kai Qin, Jiaqi Wu, Jianxiang He, Haoyuan Sun, Yifei Zhao, Bin Liang, Yongzhe Chang, Tiantian Zhang, Houde Liu
- Date: 2025-10
- Venue: -
- Code: -
- MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
- Author(s): Chenlu Ding, Jiancan Wu, Leheng Sheng, Fan Zhang, Yancheng Yuan, Xiang Wang, Xiangnan He
- Date: 2025-10
- Venue: -
- Code: -
- Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
- Author(s): Fatmazohra Rezkellah, Ramzi Dakhmouche
- Date: 2025-10
- Venue: -
- Code: -
- Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
- Author(s): Yicheng Lang, Yihua Zhang, Chongyu Fan, Changsheng Wang, Jinghan Jia, Sijia Liu
- Date: 2025-10
- Venue: -
- Code: -
- KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
- Author(s): Yinyi Luo, Zhexian Zhou, Hao Chen, Kai Qiu, Marios Savvides, Sharon Li, Jindong Wang
- Date: 2025-10
- Venue: -
- Code: -
- Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
- Author(s): Hong kyu Lee, Ruixuan Liu, Li Xiong
- Date: 2025-09
- Venue: -
- Code: -
- Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions
- Author(s): Junbeom Kim, Kyuyoung Kim, Jihoon Tack, Dongha Lim, Jinwoo Shin
- Date: 2025-09
- Venue: -
- Code: -
- Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
- Author(s): Xiang Zhang, Kun Wei, Xu Yang, Chenghao Xu, Su Yan, Cheng Deng
- Date: 2025-09
- Venue: -
- Code: -
- Mitigating Biases in Language Models via Bias Unlearning
- Author(s): Dianqing Liu, Yi Liu, Guoqing Jin, Zhendong Mao
- Date: 2025-09
- Venue: -
- Code: -
- Understanding the Dilemma of Unlearning for Large Language Models
- Author(s): Qingjie Zhang, Haoting Qian, Zhicong Huang, Cheng Hong, Minlie Huang, Ke Xu, Chao Zhang, Han Qiu
- Date: 2025-09
- Venue: -
- Code: -
- Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs
- Author(s): Arpit Garg, Hemanth Saratchandran, Ravi Garg, Simon Lucey
- Date: 2025-09
- Venue: -
- Code: -
- Dual-Space Smoothness for Robust and Balanced LLM Unlearning
- Author(s): Han Yan, Zheyuan Liu, Meng Jiang
- Date: 2025-09
- Venue: -
- Code: -
- OFMU: Optimization-Driven Framework for Machine Unlearning
- Author(s): Sadia Asif, Mohammad Mohammadi Amiri
- Date: 2025-09
- Venue: -
- Code: -
- Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
- Author(s): Nakyeong Yang, Dong-Kyum Kim, Jea Kwon, Minsung Kim, Kyomin Jung, Meeyoung Cha
- Date: 2025-09
- Venue: -
- Code: -
- CLUE: Conflict-guided Localization for LLM Unlearning Framework
- Author(s): Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang
- Date: 2025-09
- Venue: -
- Code: -
- Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
- Author(s): Wenhan Wu, Zheyuan Liu, Chongyang Gao, Ren Wang, Kaize Ding
- Date: 2025-09
- Venue: -
- Code: -
- Intrinsic Meets Extrinsic Fairness: Assessing the Downstream Impact of Bias Mitigation in Large Language Models
- Author(s): 'Mina Arzaghi', 'Alireza Dehghanpour Farashah', 'Florian Carichon', ' Golnoosh Farnadi'
- Date: 2025-09
- Venue: -
- Code: -
- Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
- Author(s): Tomoya Yamashita, Akira Ito, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara
- Date: 2025-09
- Venue: -
- Code: -
- Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
- Author(s): Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara, Tomoharu Iwata
- Date: 2025-09
- Venue: -
- Code: -
- Reveal and Release: Iterative LLM Unlearning with Self-generated Data
- Author(s): Linxi Xie, Xin Teng, Shichang Ke, Hongyi Wen, Shengjie Wang
- Date: 2025-09
- Venue: -
- Code: -
- Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
- Author(s): Zhaoyang Chu, Yao Wan, Zhikun Zhang, Di Wang, Zhou Yang, Hongyu Zhang, Pan Zhou, Xuanhua Shi, Hai Jin, David Lo
- Date: 2025-09
- Venue: -
- Code: -
- Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
- Author(s): Filip Sondej, Yushi Yang
- Date: 2025-09
- Venue: -
- Code: -
- Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning
- Author(s): Haichao Zhang, Chong Zhang, Peiyu Hu, Shi Qiu, Jia Wang
- Date: 2025-09
- Venue: -
- Code: -
- AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs
- Author(s): Debdeep Sanyal, Manodeep Ray, Murari Mandal
- Date: 2025-09
- Venue: -
- Code: -
- CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
- Author(s): Aysenur Kocak, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci
- Date: 2025-09
- Venue: -
- Code: -
- Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
- Author(s): Qinyan Zhang, Xinping Lei, Ruijie Miao, Yu Fu, Haojie Fan, Le Chang, Jiafan Hou, Dingling Zhang, Zhongfei Hou, Ziqiang Yang, Changxin Pu, Fei Hu, Jingkai Liu, Mengyun Liu, Yang Liu, Xiang Gao, Jiaheng Liu, Tong Yang, Zaiyuan Wang, Ge Zhang, Wenhao Huang
- Date: 2025-09
- Venue: -
- Code: -
- Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
- Author(s): Naman Deep Singh, Maximilian Müller, Francesco Croce, Matthias Hein
- Date: 2025-09
- Venue: -
- Code: -
- Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning
- Author(s): Praveen Bushipaka, Lucia Passaro, Tommaso Cucinotta
- Date: 2025-08
- Venue: -
- Code: -
- CURE: A Unified Framework for Class and Concept Unlearning via Retraining Emulation
- Author(s): Yiran Jia, Eric Yeats, Darryl Hannan, Aaron Jacobson, Timothy Doster, Henry Kvinge, Scott Mahan
- Date: 2025-09
- Venue: -
- Code: -
- Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
- Author(s): Yejin Kim, Eunwon Kim, Buru Chang, Junsuk Choe
- Date: 2025-08
- Venue: -
- Code: -
- Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Aware Unlearning with Proxy Constraint
- Author(s): Zhihao Liu, Jian Lou, Yuke Hu, Xiaochen Li, Tailun Chen, Yitian Chen, Zhan Qin
- Date: 2025-08
- Venue: -
- Code: -
- Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery
- Author(s): Robert Yang
- Date: 2025-08
- Venue: -
- Code: -
- Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
- Author(s): Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun
- Date: 2025-08
- Venue: -
- Code: -
- SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
- Author(s): Xiangman Li, Xiaodong Wu, Qi Li, Jianbing Ni, Rongxing Lu
- Date: 2025-08
- Venue: -
- Code: -
- CRISP: Persistent Concept Unlearning via Sparse Autoencoders
- Author(s): Tomer Ashuach, Dana Arad, Aaron Mueller, Martin Tutek, Yonatan Belinkov
- Date: 2025-08
- Venue: -
- Code: -
- Unlearning at Scale: Implementing the Right to be Forgotten in Large Language Models
- Author(s): Abdullah X
- Date: 2025-08
- Venue: -
- Code: -
- Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
- Author(s): Fuyao Zhang, Xinyu Yan, Tiantong Wu, Wenjie Li, Tianxiang Chen, Yang Cao, Ran Yan, Longtao Huang, Wei Yang Bryan Lim, Qiang Yang
- Date: 2025-08
- Venue: -
- Code: -
- Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
- Author(s): Stanley Ngugi
- Date: 2025-08
- Venue: -
- Code: -
- Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
- Author(s): Kyle O'Brien, Stephen Casper, Quentin Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman
- Date: 2025-08
- Venue: -
- Code:
- LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection
- Author(s): Ameya Anjarlekar, Sandeep Pombra
- Date: 2025-08
- Venue: -
- Code: -
- LLM Unlearning Without an Expert Curated Dataset
- Author(s): Xiaoyuan Zhu, Muru Zhang, Ollie Liu, Robin Jia, Willie Neiswanger
- Date: 2025-08
- Venue: -
- Code: -
- Analyzing and Mitigating Object Hallucination: A Training Bias Perspective
- Author(s): Yifan Li, Kun Zhou, Wayne Xin Zhao, Lei Fang, Ji-Rong Wen
- Date: 2025-08
- Venue: -
- Code: -
- From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models
- Author(s): Dunyuan Xu, Xikai Yang, Yaoqian Li, Jinpeng Li, Pheng-Ann Heng
- Date: 2025-08
- Venue: -
- Code: -
- DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
- Author(s): Man Hu, Yahui Ding, Yatao Yang, Liangyu Chen, Yanhao Jia, Shuai Zhao
- Date: 2025-08
- Venue: -
- Code: -
- Towards Evaluation for Real-World LLM Unlearning
- Author(s): Ke Miao, Yuke Hu, Xiaochen Li, Wenjie Bao, Zhihao Liu, Zhan Qin, Kui Ren
- Date: 2025-08
- Venue: -
- Code: -
- Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
- Author(s): Ziqian Zhong, Aditi Raghunathan
- Date: 2025-07
- Venue: -
- Code: -
- iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss
- Author(s): Yujian Sun, Tian Li
- Date: 2025-07
- Venue: -
- Code: -
- What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests
- Author(s): Dimitri Staufer
- Date: 2025-07
- Venue: ECML PKDD 2025 (XKDD Workshop)
- Code: -
- Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
- Author(s): Eric Yeats, Darryl Hannan, Henry Kvinge, Timothy Doster, Scott Mahan
- Date: 2025-07
- Venue: -
- Code: -
- The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
- Author(s): Alexander Xiong, Xuandong Zhao, Aneesh Pappu, Dawn Song
- Date: 2025-07
- Venue: -
- Code: -
- Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
- Author(s): Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan Günnemann
- Date: 2025-07
- Venue: -
- Code: -
- Unlearning the Noisy Correspondence Makes CLIP More Robust
- Author(s): Haochen Han, Alex Jinpeng Wang, Peijun Ye, Fangming Liu
- Date: 2025-07
- Venue: -
- Code: -
- PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning
- Author(s): Tatsuki Kawakami, Kazuki Egashira, Atsuyuki Miyai, Go Irie, Kiyoharu Aizawa
- Date: 2025-07
- Venue: -
- Code: -
- Agents Are All You Need for LLM Unlearning
- Author(s):Debdeep Sanyal, Murari Mandal
- Date: 2025-07
- Venue: -
- Code: -
- Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
- Author(s): Aly M. Kassem, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi
- Date: 2025-07
- Venue: -
- Code: -
- SoK: Semantic Privacy in Large Language Models
- Author(s): Baihe Ma, Yanna Jiang, Xu Wang, Guangsheng Yu, Qin Wang, Caijun Sun, Chen Li, Xuelei Qi, Ying He, Wei Ni, Ren Ping Liu
- Date: 2025-06
- Venue: -
- Code: -
- Model State Arithmetic for Machine Unlearning
- Author(s): Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi
- Date: 2025-06
- Venue: -
- Code: -
- Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
- Author(s): Yash Sinha, Manit Baser, Murari Mandal, Dinil Mon Divakaran, Mohan Kankanhalli
- Date: 2025-06
- Venue: -
- Code: -
- Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack
- Author(s): Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, Suhang Wang
- Date: 2025-06
- Venue: -
- Code: -
- Large Language Model Unlearning for Source Code
- Author(s): Xue Jiang, Yihong Dong, Zheng Fang, Yingwei Ma, Tangxinyu Wang, Rongyu Cao, Binhua Li, Zhi Jin, Wenpin Jiao, Yongbin Li, Ge Li
- Date: 2025-06
- Venue: -
- Code: -
- Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU
- Author(s): Arjun Dosajh, Mihika Sanghi
- Date: 2025-06
- Venue: -
- Code: -
- BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
- Author(s): Shengyuan Hu, Neil Kale, Pratiksha Thaker, Yiwei Fu, Steven Wu, Virginia Smith
- Date: 2025-06
- Venue: -
- Code: -
- Learning-Time Encoding Shapes Unlearning in LLMs
- Author(s): Ruihan Wu, Konstantin Garov, Kamalika Chaudhuri
- Date: 2025-06
- Venue: -
- Code: -
- Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
- Author(s): Yiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu, Sijia Liu
- Date: 2025-06
- Venue: -
- Code: -
- Align-then-Unlearn: Embedding Alignment for LLM Unlearning
- Author(s): Philipp Spohn, Leander Girrbach, Jessica Bader, Zeynep Akata
- Date: 2025-06
- Venue: -
- Code: -
- Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
- Author(s): Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic
- Date: 2025-06
- Venue: -
- Code:
- Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
- Author(s): Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
- Date: 2025-06
- Venue: -
- Code:
- OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
- Author(s): Vineeth Dorna, Anmol Mekala, Wenlong Zhao, Andrew McCallum, Zachary C. Lipton, J. Zico Kolter, Pratyush Maini
- Date: 2025-06
- Venue: -
- Code: -
- Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
- Author(s): Filip Sondej, Yushi Yang, Mikołaj Kniejski, Marcel Windys
- Date: 2025-06
- Venue: -
- Code: -
- UCD: Unlearning in LLMs via Contrastive Decoding
- Author(s): Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson
- Date: 2025-06
- Venue: -
- Code: -
- Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models
- Author(s): Yuwen Tan, Boqing Gong
- Date: 2025-06
- Venue: -
- Code:
- GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
- Author(s): Evelyn Ma, Duo Zhou, Peizhi Niu, Huiting Zhou, Huan Zhang, Olgica Milenkovic, S. Rasoul Etesami
- Date: 2025-06
- Venue: -
- Code: -
- SoK: Machine Unlearning for Large Language Models
- Author(s): Jie Ren, Yue Xing, Yingqian Cui, Charu C. Aggarwal, Hui Liu
- Date: 2025-06
- Venue: -
- Code: -
- BLUR: A Bi-Level Optimization Approach for LLM Unlearning
- Author(s): Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong
- Date: 2025-06
- Venue: -
- Code: -
- LLM Unlearning Should Be Form-Independent
- Author(s): Xiaotian Ye, Mengqi Zhang, Shu Wu
- Date: 2025-06
- Venue: -
- Code: -
- RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality
- Author(s): Chenlong Zhang, Zhuoran Jin, Hongbang Yuan, Jiaheng Wei, Tong Zhou, Kang Liu, Jun Zhao, Yubo Chen
- Date: 2025-06
- Venue: -
- Code: -
- Distillation Robustifies Unlearning
- Author(s): Bruce W. Lee, Addie Foote, Alex Infanger, Leni Shor, Harish Kamath, Jacob Goldman-Wetzler, Bryce Woodworth, Alex Cloud, Alexander Matt Turner
- Date: 2025-06
- Venue: -
- Code: -
- Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
- Author(s): Cheng-Long Wang, Qi Li, Zihang Xiang, Yinzhi Cao, Di Wang
- Date: 2025-06
- Venue: -
- Code: -
- Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
- Author(s): Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu, Ruihan Wu, Haoteng Yin, Mohsen Ghassemi, Yifan Li, Vamsi K. Potluru, Eli Chien, Kamalika Chaudhuri, Olgica Milenkovic, Pan Li
- Date: 2025-06
- Venue: -
- Code: -
- Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
- Author(s): Taha Entesari, Arman Hatami, Rinat Khaziev, Anil Ramakrishna, Mahyar Fazlyab
- Date: 2025-06
- Venue: -
- Code: -
- Quantifying Cross-Modality Memorization in Vision-Language Models
- Author(s): Yuxin Wen, Yangsibo Huang, Tom Goldstein, Ravi Kumar, Badih Ghazi, Chiyuan Zhang
- Date: 2025-06
- Venue: -
- Code: -
- Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs
- Author(s): Aleksey Kudelya, Alexander Shirnin
- Date: 2025-06
- Venue: -
- Code: -
- Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
- Author(s): Liang Chen, Xueting Han, Li Shen, Jing Bai, Kam-Fai Wong
- Date: 2025-06
- Venue: -
- Code: -
- Not All Tokens Are Meant to Be Forgotten
- Author(s): Xiangyu Zhou, Yao Qiang, Saleh Zare Zade, Douglas Zytko, Prashant Khanduri, Dongxiao Zhu
- Date: 2025-06
- Venue: -
- Code: -
- Rethinking Post-Unlearning Behavior of Large Vision-Language Models
- Author(s): Minsung Kim, Nakyeong Yang, Kyomin Jung
- Date: 2025-06
- Venue: -
- Code: -
- Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- Author(s): Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu
- Date: 2025-06
- Venue: -
- Code: -
- Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
- Author(s): Yixin Wan, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Rahul Gupta
- Date: 2025-06
- Venue: -
- Code: -
- Existing Large Language Model Unlearning Evaluations Are Inconclusive
- Author(s): Zhili Feng, Yixuan Even Xu, Alexander Robey, Robert Kirk, Xander Davies, Yarin Gal, Avi Schwarzschild, J. Zico Kolter
- Date: 2025-06
- Venue: -
- Code: -
- Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
- Author(s): Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu
- Date: 2025-06
- Venue: -
- Code: -
- Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
- Author(s): Lihao Sun, Chengzhi Mao, Valentin Hofmann, Xuechunzi Bai
- Date: 2025-06
- Venue: -
- Code: -
- Model Unlearning via Sparse Autoencoder Subspace Guided Projections
- Author(s): Xu Wang, Zihao Li, Benyou Wang, Yan Hu, Difan Zou
- Date: 2025-05
- Venue: -
- Code: -
- Breaking the Gold Standard: Extracting Forgotten Data under Exact Unlearning in Large Language Models
- Author(s): Xiaoyu Wu, Yifei Pang, Terrance Liu, Zhiwei Steven Wu
- Date: 2025-05
- Venue: -
- Code: -
- Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs
- Author(s): Haokun Chen, Yueqi Zhang, Yuan Bi, Yao Zhang, Tong Liu, Jinhe Bi, Jian Lan, Jindong Gu, Claudia Grosser, Denis Krompass, Nassir Navab, Volker Tresp
- Date: 2025-05
- Venue: -
- Code: -
- From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
- Author(s): Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou
- Date: 2025-05
- Venue: -
- Code: -
- Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
- Author(s): Zexi Li, Xiangzhu Wang, William F. Shen, Meghdad Kurmanji, Xinchi Qiu, Dongqi Cai, Chao Wu, Nicholas D. Lane
- Date: 2025-05
- Venue: -
- Code: -
- Graceful Forgetting in Generative Language Models
- Author(s): Chunyang Jiang, Chi-min Chan, Yiyang Cai, Yulong Liu, Wei Xue, Yike Guo
- Date: 2025-05
- Venue: -
- Code: -
- Safety Alignment via Constrained Knowledge Unlearning
- Author(s): Zesheng Shi, Yucheng Zhou, Jing Li
- Date: 2025-05
- Venue: -
- Code: -
- T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models
- Author(s): Xiaoyu Ye, Songjie Cheng, Yongtao Wang, Yajiao Xiong, Yishen Li
- Date: 2025-05
- Venue: -
- Code: -
- Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
- Author(s): Bang Trinh Tran To, Thai Le
- Date: 2025-05
- Venue: -
- Code: -
- Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
- Author(s): Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Haibo Hu, Minxin Du
- Date: 2025-05
- Venue: -
- Code: -
- CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
- Author(s): Biao Yi, Tiansheng Huang, Baolei Zhang, Tong Li, Lihai Nie, Zheli Liu, Li Shen
- Date: 2025-05
- Venue: -
- Code: -
- Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
- Author(s): Hwiyeong Lee, Uiji Hwang, Hyelim Lim, Taeuk Kim
- Date: 2025-05
- Venue: -
- Code: -
- Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value
- Author(s): Le Ma, Shirao Yang, Zihao Wang, Yinggui Wang, Lei Wang, Tao Wei, Kejun Zhang
- Date: 2025-05
- Venue: -
- Code: -
- UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
- Author(s): Miao Yu, Liang Lin, Guibin Zhang, Xinfeng Li, Junfeng Fang, Ningyu Zhang, Kun Wang, Yang Wang
- Date: 2025-05
- Venue: -
- Code:
- R-TOFU: Unlearning in Large Reasoning Models
- Author(s): Sangyeon Yoon, Wonje Jeung, Albert No
- Date: 2025-05
- Venue: -
- Code: -
- DUSK: Do Not Unlearn Shared Knowledge
- Author(s): Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Soeun Kim, Seungju Han, Youngjae Yu, Albert No
- Date: 2025-05
- Venue: -
- Code: -
- SEPS: A Separability Measure for Robust Unlearning in LLMs
- Author(s): Wonje Jeung, Sangyeon Yoon, Albert No
- Date: 2025-05
- Venue: -
- Code: -
- GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection
- Author(s): Zhijie Deng, Chris Yuhao Liu, Zirui Pang, Xinlei He, Lei Feng, Qi Xuan, Zhaowei Zhu, Jiaheng Wei
- Date: 2025-05
- Venue: -
- Code: -
- Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
- Author(s): Puning Yang, Qizhou Wang, Zhuo Huang, Tongliang Liu, Chengqi Zhang, Bo Han
- Date: 2025-05
- Venue: -
- Code:
- Layered Unlearning for Adversarial Relearning
- Author(s): Timothy Qian, Vinith Suriyakumar, Ashia Wilson, Dylan Hadfield-Menell
- Date: 2025-05
- Venue: -
- Code:
- Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
- Author(s): Stefan Vasilev, Christian Herold, Baohao Liao, Seyyed Hadi Hashemi, Shahram Khadivi, Christof Monz
- Date: 2025-05
- Venue: -
- Code: -
- WaterDrum: Watermarking for Data-centric Unlearning Metric
- Author(s): Xinyang Lu, Xinyuan Niu, Gregory Kang Ruey Lau, Bui Thi Cam Nhung, Rachael Hwee Ling Sim, Fanyu Wen, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low
- Date: 2025-05
- Venue: -
- Code:
- OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
- Author(s): Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu
- Date: 2025-05
- Venue: -
- Code:
- Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?
- Author(s): Guangzhi Sun, Potsawee Manakul, Xiao Zhan, Mark Gales
- Date: 2025-05
- Venue: -
- Code:
- Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
- Author(s): Vaidehi Patil, Yi-Lin Sung, Peter Hase, Jie Peng, Tianlong Chen, Mohit Bansal
- Date: 2025-05
- Venue: -
- Code:
- Token-Level Knowledge Unlearning for Large Language Model Security
- Author(s): Xin Song, Yong Liao
- Date: 2025-05
- Venue: CENet 2024
- Code: -
- AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
- Author(s): Zikui Cai, Shayan Shabihi, Bang An, Zora Che, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein, Furong Huang
- Date: 2025-04
- Venue: -
- Code:
- DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
- Author(s): Xuyang Zhong, Haochen Luo, Chen Liu
- Date: 2025-04
- Venue: -
- Code: -
- ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
- Author(s): Tong Chen, Faeze Brahman, Jiacheng Liu, Niloofar Mireshghallah, Weijia Shi, Pang Wei Koh, Luke Zettlemoyer, Hannaneh Hajishirzi
- Date: 2025-04
- Venue: -
- Code:
- DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
- Author(s): Tamim Al Mahmud, Najeeb Jebreel, Josep Domingo-Ferrer, David Sanchez
- Date: 2025-04
- Venue: -
- Code: -
- A mean teacher algorithm for unlearning of language models
- Author(s): Yegor Klochkov
- Date: 2025-04
- Venue: -
- Code: -
- SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation
- Author(s): Saransh Agrawal, Kuan-Hao Huang
- Date: 2025-04
- Venue: -
- Code: -
- GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs
- Author(s): Kun-Woo Kim, Ji-Hoon Park, Ju-Min Han, Seong-Whan Lee
- Date: 2025-04
- Venue: -
- Code: -
- When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
- Author(s): Hongkang Li, Yihua Zhang, Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen
- Date: 2025-04
- Venue: ICLR 2025
- Code: -
- LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
- Author(s): Soumyadeep Pal, Changsheng Wang, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
- Date: 2025-04
- Venue: -
- Code:
- SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
- Author(s): Aashiq Muhamed, Jacopo Bonato, Mona Diab, Virginia Smith
- Date: 2025-04
- Venue: -
- Code:
- Bridging the Gap Between Preference Alignment and Machine Unlearning
- Author(s): Xiaohua Feng, Yuyuan Li, Huwei Ji, Jiaming Zhang, Li Zhang, Tianyu Du, Chaochao Chen
- Date: 2025-04
- Venue: -
- Code: -
- A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
- Author(s): Xiaohua Feng, Yuyuan Li, Chengye Wang, Junlin Liu, Li Zhang, Chaochao Chen
- Date: 2025-04
- Venue: -
- Code: -
- Not All Data Are Unlearned Equally
- Author(s): Aravind Krishnan, Siva Reddy, Marius Mosbach
- Date: 2025-04
- Venue: -
- Code:
- Exact Unlearning of Finetuning Data via Model Merging at Scale
- Author(s): Kevin Kuo, Amrith Setlur, Kartik Srinivas, Aditi Raghunathan, Virginia Smith
- Date: 2025-04
- Venue: -
- Code: -
- Gradual Negative Matching for LLM Unlearning
- Author(s): Hrishikesh Kulkarni, Nazli Goharian, Ophir Frieder
- Date: 2025-04
- Venue: ECIR 2025
- Code:
- SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
- Author(s): Tianyang Xu, Xiaoze Liu, Feijie Wu, Xiaoqian Wang, Jing Gao
- Date: 2025-03
- Venue: -
- Code: -
- Effective Skill Unlearning through Intervention and Abstention
- Author(s): Yongce Li, Chung-En Sun, Tsui-Wei Weng
- Date: 2025-03
- Venue: -
- Code: -
- ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
- Author(s): Haoming Xu, Shuxun Wang, Yanqiu Zhao, Yi Zhong, Ziyan Jiang, Ningyuan Zhao, Shumin Deng, Huajun Chen, Ningyu Zhang
- Date: 2025-03
- Venue: -
- Code: -
- Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
- Author(s): Àlex Pujol Vidal, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund
- Date: 2025-03
- Venue: -
- Code: -
- Deep Contrastive Unlearning for Language Models
- Author(s): Estrid He, Tabinda Sarwar, Ibrahim Khalil, Xun Yi, Ke Wang
- Date: 2025-03
- Venue: -
- Code: -
- SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
- Author(s): Qing Li, Jiahui Geng, Derui Zhu, Fengyu Cai, Chenyang Lyu, Fakhri Karray
- Date: 2025-03
- Venue: -
- Code: -
- Atyaephyra at SemEval-2025 Task 4: Low-Rank NPO
- Author(s): Jan Bronec, Jindřich Helcl
- Date: 2025-03
- Venue: -
- Code: -
- PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
- Author(s): Zhaopan Xu, Pengfei Zhou, Weidong Tang, Jiaxin Ai, Wangbo Zhao, Xiaojiang Peng, Kai Wang, Yang You, Wenqi Shao, Hongxun Yao, Kaipeng Zhang
- Date: 2025-03
- Venue: -
- Code: -
- Hyperbolic Safety-Aware Vision-Language Models
- Author(s): Tobia Poppi, Tejaswi Kasarla, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara
- Date: 2025-03
- Venue: -
- Code: -
- Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning
- Author(s): Yiwei Chen, Yuguang Yao, Yihua Zhang, Bingquan Shen, Gaowen Liu, Sijia Liu
- Date: 2025-03
- Venue: -
- Code: -
- Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
- Author(s): Matthew Khoriaty, Andrii Shportko, Gustavo Mercier, Zach Wood-Doughty
- Date: 2025-03
- Venue: -
- Code: -
- SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
- Author(s): Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda
- Date: 2025-03
- Venue: -
- Code: -
- GRU: Mitigating the Trade-off between Unlearning and Retention for Large Language Models
- Author(s): Yue Wang, Qizhou Wang, Feng Liu, Wei Huang, Yali Du, Xiaojiang Du, Bo Han
- Date: 2025-03
- Venue: -
- Code: -
- Cyber for AI at SemEval-2025 Task 4: Forgotten but Not Lost: The Balancing Act of Selective Unlearning in Large Language Models
- Author(s): Dinesh Srivasthav P, Bala Mallikarjunarao Garlapati
- Date: 2025-03
- Venue: -
- Code: -
- UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
- Author(s): Wenyu Wang, Mengqi Zhang, Xiaotian Ye, Zhaochun Ren, Zhumin Chen, Pengjie Ren
- Date: 2025-03
- Venue: -
- Code: -
- Improving LLM Safety Alignment with Dual-Objective Optimization
- Author(s): Xuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song
- Date: 2025-03
- Venue: -
- Code:
- AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking
- Author(s): Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Athanasios Voulodimos, Giorgos Stamou
- Date: 2025-03
- Venue: -
- Code:
- CE-U: Cross Entropy Unlearning
- Author(s): Bo Yang
- Date: 2025-03
- Venue: -
- Code: -
- Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning
- Author(s): Ayana Niwa, Masahiro Kaneko, Kentaro Inui
- Date: 2025-02
- Venue: -
- Code: -
- Erasing Without Remembering: Safeguarding Knowledge Forgetting in Large Language Models
- Author(s): Huazheng Wang, Yongcheng Jing, Haifeng Sun, Yingjie Wang, Jingyu Wang, Jianxin Liao, Dacheng Tao
- Date: 2025-02
- Venue: -
- Code: -
- Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
- Author(s): Toan Tran, Ruixuan Liu, Li Xiong
- Date: 2025-02
- Venue: -
- Code: -
- Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
- Author(s): Qizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han, Kilian Q. Weinberger
- Date: 2025-02
- Venue: -
- Code: -
- FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
- Author(s): Nakyeong Yang, Minsung Kim, Seunghyun Yoon, Joongbo Shin, Kyomin Jung
- Date: 2025-02
- Venue: -
- Code: -
- [Holistic