mlsanityData to 7 Oct 2026

Large Language Model Unlearning

arXiv 2310.10683 ↗First posted 14 Oct 2023cs.CL cs.AI cs.LGcited by 288

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful responses, (2) erasing copyright-protected content as requested, and (3) reducing hallucinations. Unlearning, as an alignment technique, has three advantages. (1) It only requires negative (e.g. harmful) examples, which are much easier and cheaper to collect (e.g. via red teaming or user reporting) than positive (e.g. helpful and often human-written) examples required in RLHF (RL from human feedback). (2) It is computationally efficient. (3) It is especially effective when we know which training samples cause the misbehavior. To the best of our knowledge, our work is among the first to explore LLM unlearning. We are also among the first to formulate the settings, goals, and evaluations in LLM unlearning. We show that if practitioners only have limited resources, and therefore the priority is to stop generating undesirable outputs rather than to try to generate desirable outputs, unlearning is particularly appealing. Despite only having negative samples, our ablation study shows that unlearning can still achieve better alignment performance than RLHF with just 2% of its computational time.

Key facts. Cited by 288 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 37 of its 56 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

37 of 56 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023In-Context Unlearning: Language Models as Few Shot Unlearners11 Oct
  2. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  3. 2022Quark: Controllable Text Generation with Reinforced Unlearning26 May
  4. 2022Zero-Shot Machine Unlearning14 Jan
  5. 2021Fast Yet Effective Machine Unlearning17 Nov
  6. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  7. 2021Machine Unlearning of Features and Labels26 Aug

Other references · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  11. 2020Extracting Training Data from Large Language Modelscited by 2,144
  12. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
18 more
  1. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  2. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  3. 2019Machine Unlearningcited by 1,020
  4. 2019When Does Label Smoothing Help?cited by 985
  5. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  6. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  7. 2019Certified Data Removal from Machine Learning Modelscited by 512
  8. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 454
  9. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  10. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  11. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  12. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  13. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 226
  14. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 146
  15. 2019On Second-Order Group Influence Functions for Black-Box Predictionscited by 78
  16. 2022Do Language Models Plagiarize?cited by 72
  17. 2022Backdoor Defense with Machine Unlearningcited by 61
  18. 2023On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codexcited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 87; 2025: 116; 2026: 84.

288 papers.

Sort:

By area:

  1. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  2. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearningcited by 484
  3. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 251
  4. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  5. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  6. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearningcited by 160
  7. 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 158
  8. 2024Tamper-Resistant Safeguards for Open-Weight LLMscited by 132
  9. 2024An Adversarial Perspective on Machine Unlearning for AI Safetycited by 113
  10. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  11. 2024Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Differencecited by 85
  12. 2024Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearningcited by 81
38 more
  1. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 77
  2. 2024Catastrophic Failure of LLM Unlearning via Quantizationcited by 76
  3. 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyondcited by 76
  4. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 71
  5. 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vectorcited by 63
  6. 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyondcited by 59
  7. 2024A Closer Look at Machine Unlearning for Large Language Modelscited by 54
  8. 2024On Large Language Model Continual Unlearningcited by 51
  9. 2024Direct Unlearning Optimization for Robust and Safe Text-to-Image Modelscited by 50
  10. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 48
  11. 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMscited by 47
  12. 2024UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AIcited by 46
  13. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  14. 2024Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Modelscited by 44
  15. 2024JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Frameworkcited by 44
  16. 2024Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Conceptscited by 39
  17. 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearningcited by 39
  18. 2024Digital Forgetting in Large Language Models: A Survey of Unlearning Methodscited by 38
  19. 2025LLM Unlearning via Neural Activation Redirectioncited by 38
  20. 2023Knowledge Unlearning for LLMs: Tasks, Methods, and Challengescited by 37
  21. 2024Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMscited by 36
  22. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  23. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  24. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  25. 2024Fast Exact Unlearning for In-Context Learning Data for LLMscited by 33
  26. 2024Offset Unlearning for Large Language Modelscited by 33
  27. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  28. 2024Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearningcited by 31
  29. 2024From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attackscited by 29
  30. 2024Undesirable Memorization in Large Language Models: A Surveycited by 29
  31. 2024Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Datasetcited by 29
  32. 2024Towards Effective Evaluations and Comparisons for LLM Unlearning Methodscited by 27
  33. 2024Corrective Machine Unlearningcited by 26
  34. 2024Protecting Your LLMs with Information Bottleneckcited by 26
  35. 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Modelscited by 25
  36. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  37. 2024Adversarial Tuning: Defending Against Jailbreak Attacks for LLMscited by 23
  38. 2024Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Surveycited by 23

50 most cited of 288 All 288 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
  2. 2024Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
  3. 2026Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
  4. 2026CAP: Controllable Alignment Prompting for Unlearning in LLMs
  5. 2026CALIBURN: Self-Calibrated LLM Unlearning Alignment
  6. 2023On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
  7. 2025SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
  8. 2024A Probabilistic Perspective on Unlearning and Alignment for Large Language Models