LLM Unlearning

LLM: Large Language Model

Large language model unlearning aims to remove targeted information, such as private data, hazardous knowledge, or memorized content, without retraining the model from scratch or damaging useful abilities. Common approaches use gradient-based fine-tuning with retention constraints, parameter or representation edits, and inference-time steering; retrieval-augmented systems can also forget by changing their external knowledge stores. Benchmarks such as TOFU, MUSE, and WMDP test forgetting alongside retained utility, while newer evaluations probe recovery through paraphrases, multi-hop reasoning, quantization, and interaction. A central challenge is that suppressing an answer does not necessarily erase the information internally, and stronger forgetting can cause collateral damage or remain reversible.

Latest papers

192 papers32 papers in the last four weeks, up 68% on the four weeks before. 0.2% of all new papers.

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Nov 25, 2025Zhen Zeng, Leijiang Gu, Zhangling Duan +4VLM Unlearning Multimodal Large Language Models
Hefei University of Technology, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China · University of Amsterdam, the Netherlands
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
Oct 6, 2025Kai Qin, Jiaqi Wu, Jianxiang He +8Preference Optimization LLM Unlearning
1Tsinghua University · 2The Hong Kong University of Science and Technology · 3Jianghuai Advanced Technology Center +1
OFMU: Optimization-Driven Framework for Machine Unlearning
Sep 26, 2025Sadia Asif, Mohammad Mohammadi AmiriBilevel Optimization Machine Unlearning
Rensselaer Polytechnic Institute
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
Aug 28, 2025Zhihao Liu, Jian Lou, Yuke Hu +6Machine Unlearning LLM Unlearning
Zhejiang University · Sun Yat-sen University · UNC Greensboro +1
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
Jun 12, 2025Peizhi Niu, Evelyn Ma, Boya Hou +5Machine Unlearning LLM Unlearning
Department of Electrical & Computer Engineering, University of Illinois Urbana-Champaign
Safety Alignment via Constrained Knowledge Unlearning
May 24, 2025Zesheng Shi, Yucheng Zhou, Jing LiLLM Safety Alignment LLM Unlearning
Harbin Institute of Technology, Shenzhen, China · University of Macau, China
SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
Apr 11, 2025Aashiq Muhamed, Jacopo Bonato, Mona Diab +1Machine Unlearning LLM Unlearning
Carnegie Mellon University · Prometeia S.p.A.
Exact Unlearning of Finetuning Data via Model Merging at Scale
Apr 6, 2025Kevin Kuo, Amrith Setlur, Kartik Srinivas +2Machine Unlearning LLM Unlearning
Computer Science Department · Machine Learning Department
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
Oct 20, 2024Shang Wang, Tianqing Zhu, Dayong Ye +1Privacy-Preserving Language Models LLM Unlearning
School of Computer Science, University of Technology Sydney · Faculty of Data Science, City University of Macau
Mitigating Memorization In Language Models
Oct 3, 2024Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6Memorization in Language Models LLM Fine-Tuning
University of Chicago · Argonne National Laboratory · Lawrence Berkeley National Laboratory +3
Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning
May 24, 2024Wenhan Chang, Tianqing Zhu, Heng Xu +2Machine Unlearning LLM Unlearning
China University of Geosciences, Wuhan, China · City University of Macau, Macau SAR, China · University of Technology Sydney, Australia
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Apr 8, 2024Weikai Lu, Ziqian Zeng, Jianwei Wang +5LLM Safety Alignment LLM Jailbreak Attacks
South China University of Technology, China · Pazhou Laboratory, China

Nov 25, 2025J/K move · Enter open · S save

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

Zhen Zeng, Leijiang Gu, Zhangling Duan, Feng Li+3

Hefei University of Technology, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China · University of Amsterdam, the Netherlands

VLM Unlearning Multimodal Large Language Models Privacy Leakage in Language Models MLLM Unlearning Machine Unlearning LLM Unlearning

Open paper AskPDF arXiv

Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training. While existing unlearning methods can remove such content, they often severely degrade the model's foundational capabilities, such as general image understanding. This critical shortfall motivates our investigation into benign memory forgetting, the precise removal of targeted, privacy-sensitive knowledge while rigorously preserving unrelated capabilities. To pioneer and evaluate progress toward this objective, we introduce S-MLLMUn Bench, the first benchmark designed to jointly and quantitatively assess an unlearning method's efficacy in knowledge erasure and the preservation of image understanding. Furthermore, we propose the Sculpted Memory Forgetting Adapter (SMFA), a new framework that enables benign memory forgetting. SMFA confines forgetting to designated memory regions, maintaining overall model performance. By initially fine-tuning the model to replace sensitive outputs with refusals, SMFA generates a memory forgetting adapter, followed by a retaining anchor-guided masking mechanism that safeguards unrelated knowledge. Extensive experiments on S-MLLMUn Bench demonstrate that existing methods fail to achieve benign forgetting, whereas our proposed SMFA serves as an effective baseline, successfully achieving targeted knowledge erasure without compromising the model's foundational visual capabilities. Code and data are available at https://github.com/zeng-zhen/S-MLLMUn.