# A Closer Look at Machine Unlearning for Large Language Models

arXiv: https://arxiv.org/abs/2410.08109 · HTML: https://mlsanity.com/paper/2410.08109/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 51 of its 65 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 51)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Tamper-Resistant Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2408.00761/) (2024)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)

## Built on by (most cited first, 30 of 56)

- [Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs](https://mlsanity.com/paper/2505.16831/) (2025)
- [A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models](https://mlsanity.com/paper/2503.01854/) (2025)
- [Security Concerns for Large Language Models: A Survey](https://mlsanity.com/paper/2505.18889/) (2025)
- [CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning](https://mlsanity.com/paper/2505.16559/) (2025)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models](https://mlsanity.com/paper/2506.05314/) (2025)
- [Improving LLM Unlearning Robustness via Random Perturbations](https://mlsanity.com/paper/2501.19202/) (2025)
- [Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding](https://mlsanity.com/paper/2511.04934/) (2025)
- [AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services](https://mlsanity.com/paper/2504.20185/) (2025)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers](https://mlsanity.com/paper/2504.15827/) (2025)
- [Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models](https://mlsanity.com/paper/2506.17279/) (2025)
- [Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting](https://mlsanity.com/paper/2510.17210/) (2025)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO](https://mlsanity.com/paper/2505.23316/) (2025)
- [LLM Unlearning Without an Expert Curated Dataset](https://mlsanity.com/paper/2508.06595/) (2025)
- [Curvature-Aware Safety Restoration In LLMs Fine-Tuning](https://mlsanity.com/paper/2511.18039/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [Understanding the Dilemma of Unlearning for Large Language Models](https://mlsanity.com/paper/2509.24675/) (2025)
- [Reinforcement Unlearning via Group Relative Policy Optimization](https://mlsanity.com/paper/2601.20568/) (2026)
- [REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop](https://mlsanity.com/paper/2602.06248/) (2026)
- [GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs](https://mlsanity.com/paper/2504.12681/) (2025)
- [Position: The Term "Machine Unlearning" Is Overused in LLMs](https://mlsanity.com/paper/2606.27379/) (2026)
- [Modular Pretraining Enables Access Control](https://mlsanity.com/paper/2607.08077/) (2026)
- [Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning](https://mlsanity.com/paper/2510.00125/) (2025)
- [LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics](https://mlsanity.com/paper/2510.07626/) (2025)
- [STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models](https://mlsanity.com/paper/2601.09281/) (2026)
- [Multi-Head Attention Is a Multi-Player Game](https://mlsanity.com/paper/2602.00861/) (2026)
- [KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models](https://mlsanity.com/paper/2602.19275/) (2026)
- [MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction](https://mlsanity.com/paper/2504.05059/) (2025)

## Abstract (arXiv)

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content from LLMs while preserving the overall performance. In this paper, we discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches. To address the issue of inadequate evaluation of model outputs after unlearning, we introduce three additional metrics to evaluate token diversity, sentence semantics, and factual correctness. We then categorize unlearning methods into untargeted and targeted, and discuss their issues respectively. Specifically, the behavior that untargeted unlearning attempts to approximate is unpredictable and may involve hallucinations, and existing regularization is insufficient for targeted unlearning. To alleviate these issues, we propose using the objective of maximizing entropy (ME) for untargeted unlearning and incorporate answer preservation (AP) loss as regularization for targeted unlearning. Experimental results across three scenarios, i.e., fictitious unlearning, continual unlearning, and real-world unlearning, demonstrate the effectiveness of our approaches. The code is available at https://github.com/sail-sg/closer-look-LLM-unlearning.