# LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models

arXiv: https://arxiv.org/abs/2409.13054 · HTML: https://mlsanity.com/paper/2409.13054/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [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)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [Temporal Effects on Pre-trained Models for Language Processing Tasks](https://mlsanity.com/paper/2111.12790/) (2021)
- [Unveiling the Pitfalls of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2310.02129/) (2023)
- [Digital Forgetting in Large Language Models: A Survey of Unlearning Methods](https://mlsanity.com/paper/2404.02062/) (2024)
- [Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey](https://mlsanity.com/paper/2310.01424/) (2023)
- [Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models](https://mlsanity.com/paper/2405.15349/) (2024)
- [Knowledge Editing in Language Models via Adapted Direct Preference Optimization](https://mlsanity.com/paper/2406.09920/) (2024)
- [Stable Knowledge Editing in Large Language Models](https://mlsanity.com/paper/2402.13048/) (2024)

## Built on by (most cited first, 5 of 5)

- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy](https://mlsanity.com/paper/2506.00359/) (2025)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew](https://mlsanity.com/paper/2605.17938/) (2026)
- [CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs](https://mlsanity.com/paper/2512.12914/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying LLMs to unlearn problematic and outdated information while efficiently integrating new knowledge without retraining from scratch. Here, we propose LLM Surgery, a framework to efficiently modify LLM behaviour by optimizing a three component objective function that: (1) Performs reverse gradient on unlearning dataset (problematic and outdated information), (2) Performs gradient descent on the update dataset (new and updated information), and (3) Minimizes the KL divergence on the retain dataset (small subset of unchanged text), ensuring alignment between pretrained and modified model outputs. Due to the lack of publicly available datasets specifically tailored for our novel task, we compiled a new dataset and an evaluation benchmark. Using Llama2-7B, we demonstrate that LLM Surgery can achieve significant forgetting on the unlearn set, a 20% increase in accuracy on the update set, and maintain performance on the retain set.