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

arXiv: https://arxiv.org/abs/2407.01920 · HTML: https://mlsanity.com/paper/2407.01920/

## Key facts

- Cited by 26 papers in the map (data through 14 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.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [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)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment](https://mlsanity.com/paper/2305.06535/) (2023)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers](https://mlsanity.com/paper/2301.11578/) (2023)

## Built on by (most cited first, 26 of 26)

- [OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics](https://mlsanity.com/paper/2506.12618/) (2025)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts](https://mlsanity.com/paper/2410.12777/) (2024)
- [ForgetMe: Evaluating Selective Forgetting in Generative Models](https://mlsanity.com/paper/2504.12574/) (2025)
- [Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy](https://mlsanity.com/paper/2506.00359/) (2025)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [Not All Tokens Are Meant to Be Forgotten](https://mlsanity.com/paper/2506.03142/) (2025)
- [Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting](https://mlsanity.com/paper/2510.17210/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop](https://mlsanity.com/paper/2602.06248/) (2026)
- [A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting](https://mlsanity.com/paper/2606.03280/) (2026)
- [MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes](https://mlsanity.com/paper/2410.08557/) (2024)
- [GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs](https://mlsanity.com/paper/2504.12681/) (2025)
- [Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs](https://mlsanity.com/paper/2510.03567/) (2025)
- [Leveraging Machine Unlearning for Cost-Efficient Preference Alignment](https://mlsanity.com/paper/2504.06659/) (2025)
- [LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning](https://mlsanity.com/paper/2607.02513/) (2026)
- [Learning-Time Encoding Shapes Unlearning in LLMs](https://mlsanity.com/paper/2506.15076/) (2025)
- [GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention](https://mlsanity.com/paper/2507.13598/) (2025)
- [Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models](https://mlsanity.com/paper/2506.11253/) (2025)
- [Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs](https://mlsanity.com/paper/2601.04275/) (2026)
- [EvoMU: Evolutionary Machine Unlearning](https://mlsanity.com/paper/2602.02139/) (2026)
- [Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating](https://mlsanity.com/paper/2603.12598/) (2026)
- [How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning](https://mlsanity.com/paper/2606.02119/) (2026)
- [CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence](https://mlsanity.com/paper/2606.27683/) (2026)
- [Extracting Forgotten Prompts from Targeted Unlearned Models](https://mlsanity.com/paper/2609.03662/) (2026)
- [Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning](https://mlsanity.com/paper/2609.37858/) (2026)

## 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.