English
Related papers

Related papers: R-TOFU: Unlearning in Large Reasoning Models

200 papers

Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method that combines reinforcement learning from AI feedback (RLAIF)…

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

Machine Learning · Computer Science 2025-06-03 Rongzhe Wei , Mufei Li , Mohsen Ghassemi , Eleonora Kreačić , Yifan Li , Xiang Yue , Bo Li , Vamsi K. Potluru , Pan Li , Eli Chien

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

Computation and Language · Computer Science 2026-05-28 Yuefeng Peng , Parnian Afshar , Megan Ganji , Thomas Butler , Amir Houmansadr , Mingxian Wang , Dezhi Hong

The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only as the very last…

Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose…

Machine Learning · Computer Science 2026-05-15 Tiantong Wang , Xinyu Yan , Tiantong Wu , Yurong Hao , Pengjun Xie , Wei Yang Bryan Lim

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

Software Engineering · Computer Science 2025-12-02 Mohammad Abdollahi , Khandaker Rifah Tasnia , Soumit Kanti Saha , Jinqiu Yang , Song Wang , Hadi Hemmati

Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex problems. However, the language space may not always be…

Computation and Language · Computer Science 2025-11-04 Shibo Hao , Sainbayar Sukhbaatar , DiJia Su , Xian Li , Zhiting Hu , Jason Weston , Yuandong Tian

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…

Machine Learning · Computer Science 2026-01-06 Xiang Zhang , Kun Wei , Xu Yang , Jiahua Li , Su Yan , Cheng Deng

Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) by generating natural language (NL) rationales that lead to the final answer. However, it struggles with numerical…

Artificial Intelligence · Computer Science 2025-02-13 Cheryl Li , Tianyuan Xu , Yiwen Guo

The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours, such as the generation of harmful, private, or incorrect…

Computation and Language · Computer Science 2025-09-03 Yihuai Hong , Lei Yu , Haiqin Yang , Shauli Ravfogel , Mor Geva

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Machine Learning · Computer Science 2026-01-21 Nyal Patel , Matthieu Bou , Arjun Jagota , Satyapriya Krishna , Sonali Parbhoo

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural…

Computation and Language · Computer Science 2025-05-27 Tingchen Fu , Jiawei Gu , Yafu Li , Xiaoye Qu , Yu Cheng

The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable…

Machine Learning · Computer Science 2025-10-10 Anu Agarwal , Mihir Pamnani , Dilek Hakkani-Tur

Traditional Large Language Model (LLM) pretraining relies on autoregressive language modeling with randomly sampled data from web-scale datasets. Inspired by human learning techniques like spaced repetition, we hypothesize that random…

Computation and Language · Computer Science 2025-01-30 Neha Prakriya , Jui-Nan Yen , Cho-Jui Hsieh , Jason Cong

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine Learning · Computer Science 2025-10-10 Yeskendir Koishekenov , Aldo Lipani , Nicola Cancedda

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit…

Machine Learning · Computer Science 2026-03-03 Saleh Zare Zade , Xiangyu Zhou , Sijia Liu , Dongxiao Zhu

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Artificial Intelligence · Computer Science 2025-05-27 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Bhaskar Ramasubramanian , Luyao Niu , Bill Yuchen Lin , Xiang Yue , Radha Poovendran

Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progress is hampered by the lack of benchmarks with rigorous,…

Computation and Language · Computer Science 2026-02-16 Haiyun Guo , Zhiyan Hou , Yandu Sun , Jinghan He , Yu Chen , Yuzhe Zhou , Yuheng Jia , Jinqiao Wang , Tat-Seng Chua