LLM Unlearning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 150% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 129

All topics

Natively Unlearnable Large Language Models
Jun 11, 2026Gaurav R. Ghosal, Pratyush Maini, Aditi RaghunathanActivation Sparsity Machine Unlearning
Carnegie Mellon University · DatologyAI
TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
Jun 11, 2026Zhengtao Yao, Liuyang Song, Hongbo Zhang +4Knowledge Editing Masked Diffusion Models
University of Southern California, USA · Peking University, China · Stevens Institute of Technology, USA +1
MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
Jun 11, 2026He Li, Haoang Chi, Qizhou Wang +6VLM Unlearning Multimodal Large Language Models
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · TMLR Group, Hong Kong Baptist University, Hong Kong, China · School of Statistics and Data Science, Shanghai University of Finance and Economics, Shanghai, China +2
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning
Jun 9, 2026Bocheng Ju, Jianhua Wang, Chengliang Liu +1Low-Rank Adaptation LLM Unlearning
Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, P.R.China · College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, China, 030024 · Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China
Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models
Jun 9, 2026Jingyi Xie, Yijun Lin, Yinjiang Xiong +2Mixture-of-Experts Language Models Machine Unlearning
Renmin University of China · Lightstandard · Zhejiang University +1
Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
Jun 4, 2026Gizem Yüce, Giorgos Nikolaou, Nicolas FlammarionMachine Unlearning LLM Unlearning
Theory of Machine Learning Lab, EPFL
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Jun 2, 2026Lisa Bouger, Théo Lasnier, Philippe Loubet Moundi +2LLM Backdoor Attacks Backdoor Defense in LLMs
1Inria Paris · 2Sorbonne Université · 3Thales CDI
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
Jun 2, 2026Clara Haya Suslik, Or Shafran, Mor GevaMachine Unlearning LLM Unlearning
Blavatnik School of Computer Science and AI, Tel Aviv University
Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
Jun 2, 2026Chaoyi Xiang, Olga Ohrimenko, Benjamin I. P. Rubinstein +1Machine Unlearning LLM Unlearning
School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia.
Fast Unlearning at Scale via Margin Self-Correction
Jun 1, 2026Federico Di Gennaro, Alexander Shevchenko, Fanny YangMachine Unlearning LLM Unlearning
ETH Zürich
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
Jun 1, 2026Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim +3Machine Unlearning LLM Unlearning
Department of Computer Science, National University of Singapore, Singapore · Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore
Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
May 29, 2026Humzah Merchant, Bradford LevyPrivacy Leakage in Language Models Memorization in Generative Models
University of Chicago, Chicago, IL 60637.
De-attribute to Forget for LLM Unlearning
May 29, 2026Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim +3Machine Unlearning LLM Unlearning
Department of Computer Science, National University of Singapore, Singapore 117417.
AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis
May 28, 2026Saeedeh Davoudi, Reihaneh Iranmanesh, Ophir Frieder +1Healthcare Privacy Leakage in Language Models
1IR Lab, Computer Science Department, Georgetown University, Washington D.C.
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
May 28, 2026Suryash Yagnik, Shubham Gaur, Saksham Thakur +3Machine Unlearning LLM Unlearning
1Indian Institute of Information Technology, Bhopal, India · University of California, Santa Cruz, USA · 3Independent Researcher +2
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
May 26, 2026Ruihao Pan, Suhang WangRefusal Behavior in Language Models Machine Unlearning
Pennsylvania State University
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
May 26, 2026Xiaotian Ye, Xiaohan Wang, Mengqi Zhang +1Knowledge Conflicts in Language Models Hallucination in Language Models
Beijing University of Posts and Telecommunications · Huazhong University of Science and Technology · Shandong University +1
Model Unlearning Objectives Vary for Distinct Language Functions
May 26, 2026Berk Atil, Vipul Gupta, Rebecca J. PassonneauLLM Safety Machine Unlearning
Pennsylvania State University · Scale AI
SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation
May 25, 2026Michael Orme, Yanchao Yu, Zhiyuan TanRL for Language Models Language Model-Based Control
School of Computing, Engineering and Building Environment. Edinburgh Napier University Edinburgh, EH10 5DT, UK
Measuring the Depth of LLM Unlearning via Activation Patching
May 23, 2026Jaeung Lee, Dohyun Kim, Jaemin JoLLM Auditing LLM Unlearning
Sungkyunkwan University Republic of Korea
Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models
May 20, 2026Divyaksh Shukla, Ashutosh ModiConfidence Estimation in Language Models Language Model Calibration
Indian Institute of Technology Kanpur (IIT Kanpur)
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
May 20, 2026Xuyang Zhong, Qizhang Li, Yiwen Guo +1Machine Unlearning Multi-Objective Optimization
Department of Computer Science, City University of Hong Kong · Independent Researcher.
OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets
May 19, 2026Haolin XueData Provenance LLM Unlearning
Machine Unlearning for Masked Diffusion Language Models
May 18, 2026Georu Lee, Seungwon Jeong, Hoki Kim +2Masked Diffusion Models Diffusion Model Unlearning
1Dongguk University-Seoul · 2Chung-Ang University · 3Korea Institute for Advanced Study
Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
May 17, 2026Yanhang Li, Zhichao Fan, Zexin ZhuangMemorization in Language Models LLM Auditing
Northeastern University, USA · University of Illinois Urbana-Champaign, USA · Southern Methodist University, USA
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
May 16, 2026Puning Yang, Junchi Yu, Qizhou Wang +3LLM Refusal LLM Safety
Department of Natural Language Processing, MBZUAI. · University of Oxford. · RIKEN Center for Advanced Intelligence Project. +1
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
May 16, 2026Yujie Lin, Chengyi Yang, Zhishang Xiang +2Privacy Leakage in Language Models Model Editing
School of Informatics, Xiamen University, China · Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China · School of Film, Xiamen University, China +2
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
May 15, 2026Jiahui Guang, Haiyan Wang, Yingjie Zhu +4VLM Unlearning Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory, Shenzhen, China · The Hong Kong Polytechnic University, Hong Kong, China +1
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
May 14, 2026Saisab Sadhu, Pratinav Seth, Vinay Kumar SankarapuMachine Unlearning Post-Training Quantization
Lexsi Labs
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
May 14, 2026Kyomin Hwang, Hyeonjin Kim, Sangyeon Cho +1Multilingual Language Model Evaluation Privacy Leakage in Language Models
GSCST, Seoul National University · Department of Artificial Intelligence, Chung-Ang University · Korean Surgical Researcher Foundation, Republic of Korea +1

Jun 11, 2026, cs.LGJ/K move · Enter open · S save

Natively Unlearnable Large Language Models

Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan

Carnegie Mellon University · DatologyAI

Activation Sparsity Machine Unlearning LLM Unlearning LLM Training

Open paper AskPDF arXiv

Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model. Isolating source contributions to disjoint parameters makes removal easier, though it obstructs joint learning across sources. We propose NULLs (Natively Unlearnable LLMs), a model class that satisfies the two opposing goals of isolating source-specific contributions and learning jointly across sources, by training a set of shared backbone neurons alongside a pool of sparsely activated sinks. During training, information specific to a source naturally concentrates in its sinks while information shared across sources accumulates in the backbone. A source is then unlearned at deployment by disabling its corresponding sinks, with no gradient updates and no access to the retained data. We show that NULLs scales to Wikipedia's ~6M articles, isolating each as an independent source. Unlearning a single article removes knowledge specific to it while preserving facts shared with semantically related articles, closely matching retraining from scratch. We note that unlearning with NULLs is also robust: in a case study of unlearning the Harry Potter books, NULLs resists both adversarial extraction and relearning that reverses post-hoc unlearning. Finally, NULLs preserves general language capabilities, matching a standard transformer on downstream benchmarks. Together, these results suggest that source-level unlearning need not be an afterthought. It can be built natively into LLM training while retaining the benefits of shared representation learning.

Momentum

Related topics

Latest papers 129