mlsanityData to 7 Oct 2026

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

arXiv 2407.01920 ↗First posted 2 Jul 2024cs.CL cs.AI cs.CVcited by 25

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. However, current unlearning paradigms are mired in vague forgetting boundaries, often erasing knowledge indiscriminately. In this work, we introduce KnowUnDo, a benchmark containing copyrighted content and user privacy domains to evaluate if the unlearning process inadvertently erases essential knowledge. Our findings indicate that existing unlearning methods often suffer from excessive unlearning. To address this, we propose a simple yet effective method, MemFlex, which utilizes gradient information to precisely target and unlearn sensitive parameters. Experimental results show that MemFlex is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs. Code and dataset are released at https://github.com/zjunlp/KnowUnDo.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 38 of its 66 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

38 of 66 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024Intrinsic Test of Unlearning Using Parametric Knowledge Traces17 Jun
  2. 2024What makes unlearning hard and what to do about it3 Jun
  3. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  4. 2024Guardrail Baselines for Unlearning in LLMs5 Mar
  5. 2024Dissecting Language Models: Machine Unlearning via Selective Pruning2 Mar
  6. 2024Towards Safer Large Language Models through Machine Unlearning15 Feb
  7. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  8. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMs31 Oct
  9. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  10. 2023In-Context Unlearning: Language Models as Few Shot Unlearners11 Oct
  11. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  12. 2023KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment11 May
2 more
  1. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers27 Jan
  2. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct

Other references · 24

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  10. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  11. 2022Mass-Editing Memory in a Transformercited by 976
  12. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
12 more
  1. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  2. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 740
  3. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  4. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  5. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  6. 2024Detoxifying Large Language Models via Knowledge Editingcited by 86
  7. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 48
  8. 2024Localizing Paragraph Memorization in Language Modelscited by 30
  9. 2024Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patchingcited by 16
  10. 2024Knowledge Localization: Mission Not Accomplished? Enter Query Localization!cited by 13
  11. 2024Demystifying Language Model Forgetting with Low-rank Example Associationscited by 8
  12. 2024Enhancing Data Privacy in Large Language Models through Private Association Editingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 11.

25 papers.

Sort:

By area:

  1. 2025OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metricscited by 80
  2. 2024A Closer Look at Machine Unlearning for Large Language Modelscited by 54
  3. 2024Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Conceptscited by 39
  4. 2025ForgetMe: Evaluating Selective Forgetting in Generative Modelscited by 11
  5. 2025Not All Tokens Are Meant to Be Forgottencited by 6
  6. 2026Attention Smoothing Is All You Need For Unlearningcited by 6
  7. 2025Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shiftingcited by 5
  8. 2025Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuningcited by 4
  9. 2026REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loopcited by 4
  10. 2024MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimescited by 3
  11. 2025GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMscited by 3
  12. 2025Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMscited by 3
13 more
  1. 2026A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Settingcited by 3
  2. 2025Leveraging Machine Unlearning for Cost-Efficient Preference Alignmentcited by 2
  3. 2026LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearningcited by 2
  4. 2025Learning-Time Encoding Shapes Unlearning in LLMscited by 1
  5. 2025Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Modelscited by 0
  6. 2025GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retentioncited by 0
  7. 2026Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMscited by 0
  8. 2026EvoMU: Evolutionary Machine Unlearningcited by 0
  9. 2026Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gatingcited by 0
  10. 2026How Hard Can It Be? Hardness-Aware Multi-Objective Unlearningcited by 0
  11. 2026CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergencecited by 0
  12. 2026Extracting Forgotten Prompts from Targeted Unlearned Modelscited by 0
  13. 2026Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearningcited by 0