# Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges

arXiv: https://arxiv.org/abs/2311.15766 · HTML: https://mlsanity.com/paper/2311.15766/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (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)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Composing Parameter-Efficient Modules with Arithmetic Operations](https://mlsanity.com/paper/2306.14870/) (2023)
- [KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment](https://mlsanity.com/paper/2305.06535/) (2023)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)

## Built on by (most cited first, 30 of 38)

- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [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)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference](https://mlsanity.com/paper/2406.08607/) (2024)
- [Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions](https://mlsanity.com/paper/2404.07214/) (2024)
- [Position: LLM Unlearning Benchmarks are Weak Measures of Progress](https://mlsanity.com/paper/2410.02879/) (2024)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs](https://mlsanity.com/paper/2408.06621/) (2024)
- [Undesirable Memorization in Large Language Models: A Survey](https://mlsanity.com/paper/2410.02650/) (2024)
- [Towards Efficient and Effective Unlearning of Large Language Models for Recommendation](https://mlsanity.com/paper/2403.03536/) (2024)
- [Large Scale Knowledge Washing](https://mlsanity.com/paper/2405.16720/) (2024)
- [Towards LifeSpan Cognitive Systems](https://mlsanity.com/paper/2409.13265/) (2024)
- [On the Limitations and Prospects of Machine Unlearning for Generative AI](https://mlsanity.com/paper/2408.00376/) (2024)
- [LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks](https://mlsanity.com/paper/2504.10185/) (2025)
- [Distillation Robustifies Unlearning](https://mlsanity.com/paper/2506.06278/) (2025)
- [Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs](https://mlsanity.com/paper/2506.14003/) (2025)
- [OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models](https://mlsanity.com/paper/2510.22535/) (2025)
- [Not All Tokens Are Meant to Be Forgotten](https://mlsanity.com/paper/2506.03142/) (2025)
- [Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2511.20196/) (2025)
- [Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models](https://mlsanity.com/paper/2502.19982/) (2025)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check](https://mlsanity.com/paper/2510.12981/) (2025)
- [Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning](https://mlsanity.com/paper/2406.04076/) (2024)
- [Data-Centric AI in the Age of Large Language Models](https://mlsanity.com/paper/2406.14473/) (2024)
- [Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems](https://mlsanity.com/paper/2410.23472/) (2024)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)

## Abstract (arXiv)

In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question answering and reasoning, their potential to retain faulty or even harmful knowledge poses risks of malicious application. The challenge of mitigating this issue and transforming these models into purer assistants is crucial for their widespread applicability. Unfortunately, Retraining LLMs repeatedly to eliminate undesirable knowledge is impractical due to their immense parameters. Knowledge unlearning, derived from analogous studies on machine unlearning, presents a promising avenue to address this concern and is notably advantageous in the context of LLMs. It allows for the removal of harmful knowledge in an efficient manner, without affecting unrelated knowledge in the model. To this end, we provide a survey of knowledge unlearning in the era of LLMs. Firstly, we formally define the knowledge unlearning problem and distinguish it from related works. Subsequently, we categorize existing knowledge unlearning methods into three classes: those based on parameter optimization, parameter merging, and in-context learning, and introduce details of these unlearning methods. We further present evaluation datasets used in existing methods, and finally conclude this survey by presenting the ongoing challenges and future directions.