LLM Unlearning

LLM: Large Language Model

Overview

Large language model unlearning aims to remove targeted information, such as private data, hazardous knowledge, or memorized content, without retraining the model from scratch or damaging useful abilities. Common approaches use gradient-based fine-tuning with retention constraints, parameter or representation edits, and inference-time steering; retrieval-augmented systems can also forget by changing their external knowledge stores. Benchmarks such as TOFU, MUSE, and WMDP test forgetting alongside retained utility, while newer evaluations probe recovery through paraphrases, multi-hop reasoning, quantization, and interaction. A central challenge is that suppressing an answer does not necessarily erase the information internally, and stronger forgetting can cause collateral damage or remain reversible.

Latest papers

CardsList

207 papers16 papers in the last four weeks, down 56% on the four weeks before. 0.1% of all new papers.

  1. CurvDelta: Low-Curvature Delta Modeling For Surgical Learning and Unlearning

    Nov 18, 2026Zeguan Xiao, Zhuocheng Liang, Yun Chen +3LLM UnlearningCurvature-Aware Optimization

  2. LEAF-OPD: Learning to Forget from Privileged Contexts via On-Policy Distillation

    Nov 16, 2026Zirui Pang, Zhijie Deng, Yuancheng Wang +4LLM UnlearningOn-Policy Distillation

  3. From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts

    Nov 14, 2026Ruihong Zeng, Puning Yang, Jinghui Zhang +4LLM UnlearningLarge Language Model-Based Role-Play Simulation

  4. Disentangling Forgetting from Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection

    Nov 13, 2026Xiuyuan Wang, Weiming Liu, Zongxin Yang +7LLM UnlearningSafety-Utility Trade-Off in Language Models

  5. ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language Models

    Nov 11, 2026Sujan Maharjan, Lu LiuLLM EvaluationAnchoring Bias in Language Models

  6. Spectral Unlearning: Transformer Structure-Preserving Updates for Language Models

    Nov 9, 2026Sung Il Choi, Junhao Cai, Dohun Kim +1Machine UnlearningLLM Unlearning

  7. Hallucination-Guided Unlearning: Using Hallucination Traces to Reveal Overfitted Memories

    Nov 7, 2026Jiayu Zhang, Ziqi Zhong, Yuliang Gai +1LLM Unlearning

  8. Auditable Unlearning for LLMs

    Nov 4, 2026Piyush Tiwary, Anushka Srivastava, Prathosh A. PMachine UnlearningLLM Unlearning

  9. Suppressing Misaligned Behaviors in Language Models, Durably

    Nov 3, 2026Luxi He, Pengcheng Jiang, Jifan Zhang +2LLM AlignmentLLM Unlearning

  10. Forget What Comes Next: LLM Unlearning via Statistical Independence

    Nov 2, 2026Andrii Shkabrii, Claudia Plant, Martin PawelczykHilbert-Schmidt Independence CriterionLLM Unlearning

  11. Adaptive Localization of Knowledge Negation for Continual LLM Unlearning

    Nov 2, 2026Abudukelimu Wuerkaixi, Qizhou Wang, Sen Cui +5Gradient SparsityContinual Machine Unlearning

  12. Unlearning by Extrapolating a Shrink-and-Heal Lookahead

    Oct 30, 2026Hoang-Chau Luong, Lingwei ChenMachine UnlearningLLM Unlearning

  13. What Should LLMs Forget: Reinforcement Unlearning of Knowledge Associations

    Oct 30, 2026Wutong Xu, Yun Qu, Haiyan Feng +2Machine UnlearningLLM Unlearning

  14. Preserving Utility in Continual LLM Unlearning via Orthogonal Projections

    Oct 29, 2026Juan Belieni, Ana Carolina Erthal, Eliezer de Souza da Silva +1LLM Unlearning

  15. TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs

    Oct 22, 2026Mengying Zhang, Derui Wang, Ibrahim Khalil +3Privacy Leakage in Language ModelsTraining Data Reconstruction Attacks

  16. Does Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM Teams

    Oct 19, 2026Hengsong Liu, Liangyu Teng, Jingnan Cai +5LLM UnlearningMachine Unlearning Evaluation

  17. CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models

    Oct 15, 2026Jingkai Guo, Ziyi Zhao, Chaitali Chakrabarti +1Machine UnlearningLLM Unlearning

  18. Behavioral Forgetting Is Not Privacy in Machine Unlearning

    Oct 15, 2026Tyler Lizzo, Larry HeckMachine UnlearningLLM Unlearning

  19. Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

    Oct 15, 2026Adnan Al Ali, Jindřich Libovický, Anne LauscherAdversarial DebiasingLanguage Model Debiasing

  20. FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning

    Oct 15, 2026Reeyansh Shah, Maram Hasan, Subhasis Chaudhuri +1Federated UnlearningMachine Unlearning

  21. MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents

    Oct 15, 2026Cheng Zhang, Xuanning Cao, Zhicheng Zheng +1LLM Agent MemoryPrivacy Leakage in Language Models

  22. Not All Change Is Damage: Update-Matched Unlearning for Large Language Models

    Oct 15, 2026Jie Li, Youming Tao, Bowei He +1Machine UnlearningLLM Unlearning

  23. RA2^2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

    Oct 14, 2026Zinan Ling, Yang Xiao, Ruimeng Ye +2Machine UnlearningLLM Unlearning

  24. Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

    Oct 13, 2026Bofan Xie, Chaokun Wang, Guanchen Ge +4LLM Agent MemoryMemory Agent Benchmarks

  25. Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents

    Oct 13, 2026Junkai Lin, Ge Xu, Zheng Xu +2Machine UnlearningLLM Unlearning

  26. Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models

    Oct 13, 2026Jingyue Cong, Andy Song, Yang Yu +7LLM UnlearningPrivacy Leakage in Language Models

  27. REDaCT: Collapse-Free Unlearning in Large Reasoning Models

    Oct 8, 2026Joshua Maccoby, Wendy Hui WangMachine UnlearningLLM Unlearning

  28. Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning

    Oct 8, 2026Xunlei Chen, Qinghui Gong, Jingkun Xue +3Machine UnlearningLLM Unlearning