Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive information in the training data such as copyrighted and private content has led to ethical and legal concerns. To address these issues, selective forgetting (also known as machine unlearning) has emerged as a potential remedy for LRMs. However, existing unlearning methods primarily target final answers and may degrade the overall reasoning ability of LRMs after forgetting. Additionally, directly applying unlearning on the entire CoTs could degrade the general reasoning capabilities. The key challenge for LRM unlearning lies in achieving precise unlearning of targeted knowledge while preserving the integrity of general reasoning capabilities. To bridge this gap, we in this paper propose a novel LRM unlearning framework that selectively removes sensitive reasoning components while preserving general reasoning capabilities. Our approach leverages multiple LLMs with retrieval-augmented generation (RAG) to analyze CoT traces, identify forget-relevant segments, and replace them with benign placeholders that maintain logical structure. We also introduce a new feature replacement unlearning loss for LRMs, which can simultaneously suppress the probability of generating forgotten content while reinforcing structurally valid replacements. Extensive experiments on both synthetic and medical datasets verify the desired properties of our proposed method.
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Hefei University of Technology(合肥工业大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);University of Amsterdam(阿姆斯特丹大学)
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
Harbin Institute of Technology(哈尔滨工业大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Unlimidata Ltd(Unlimidata有限公司);The Chinese University of Hong Kong(香港中文大学);University of Calabria(卡拉布里亚大学)
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning
School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);Tencent(腾讯);Center for Language AI Research, Tohoku University(东北大学语言人工智能研究中心);RIKEN Center for Advanced Intelligence Project(日本理化学研究所先进人工智能项目中心)
Mila - Quebec AI Institute(魁北克人工智能研究所);Polytechnique Montréal(蒙特利尔理工学院);Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);CIFAR AI Chair(CIFAR人工智能主席);Google DeepMind(谷歌DeepMind)
Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
College of Zhiyuan, Shanghai Jiao Tong University(上海交通大学致远学院);School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院);Shanghai Jiao Tong University(上海交通大学)
Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning
School of Computer Science, University of Nottingham, Nottingham, United Kingdom(诺丁汉大学计算机科学学院);School of Informatics and Computing, Northern Arizona University, Flagstaff, United States of America(北亚利桑那大学信息学院);School of Computer Science, University of Nottingham, Ningbo, China(诺丁汉大学宁波校区)
MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Southeast University(东南大学);School of Computing, National University of Singapore(新加坡国立大学计算机学院)
SeLaR: Selective Latent Reasoning in Large Language Models
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology(广东省超高清沉浸式媒体技术重点实验室);Shenzhen Graduate School, Peking University(北京大学深圳研究生院)
Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
University of Technology Sydney(悉尼科技大学);East China Normal University(华东师范大学);The University of New South Wales(新南威尔士大学);Shanghai Jiaotong University(上海交通大学);The Education University of Hong Kong(香港教育大学)
Lifelong Learning and Selective Forgetting via Contrastive Strategy
University of Chinese Academy of Sciences(中国科学院大学);Nanjing University of Posts and Telecommunications(南京邮电大学);Beijing University of Posts and Telecommunications(北京邮电大学)
To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering
Department of Electrical and Computer Engineering(电气与计算机工程系);University of Minnesota(明尼苏达大学);Division of Computational Health Sciences, Department of Surgery(计算健康科学 division,外科系);Department of Computer Science and Engineering(计算机科学与工程系);Health Data Science, School of Public Health(公共卫生学院健康数据科学系)
Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
School of Economics and Management, East China Normal University(华东师范大学经济与管理学部);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(Mohamed bin Zayed人工智能大学);University of Queensland(昆士兰大学);Provable Responsible AI and Data Analytics (PRADA) Lab(可证明责任人工智能与数据分析实验室);King Abdullah University of Science and Technology (KAUST)(卡塔尔科学与技术大学)
Talking to Yourself: Defying Forgetting in Large Language Models
Zhejiang University(浙江大学);Binjiang Institute of Zhejiang University(浙江大学滨江学院);Om AI Research(奥姆人工智能研究);Stanford University(斯坦福大学);ETH Zürich(苏黎世联邦理工学院)
Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
Department of Mathematics, University of California Davis, USA(加州大学戴维斯分校数学系);SLAC National Accelerator Laboratory, Stanford University, USA(斯坦福大学SLAC国家加速器实验室);Department of Computer Science, University of California Davis, USA(加州大学戴维斯分校计算机科学系)