English
Related papers

Related papers: Unlearners Can Lie: Evaluating and Improving Hones…

200 papers

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Computation and Language · Computer Science 2024-11-01 Chris Yuhao Liu , Yaxuan Wang , Jeffrey Flanigan , Yang Liu

Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been…

Machine Learning · Computer Science 2025-06-12 Jie Ren , Yue Xing , Yingqian Cui , Charu C. Aggarwal , Hui Liu

We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model…

Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding model competence). Current LLMs often conflate these…

Computation and Language · Computer Science 2026-02-03 Dengyun Peng , Qiguang Chen , Bofei Liu , Jiannan Guan , Libo Qin , Zheng Yan , Jinhao Liu , Jianshu Zhang , Wanxiang Che

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishonesty in helpful and…

Computation and Language · Computer Science 2024-06-06 Youcheng Huang , Jingkun Tang , Duanyu Feng , Zheng Zhang , Wenqiang Lei , Jiancheng Lv , Anthony G. Cohn

As large language models (LLMs) become more capable and agentic, the requirement for trust in their outputs grows significantly, yet at the same time concerns have been mounting that models may learn to lie in pursuit of their goals. To…

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical…

Computation and Language · Computer Science 2025-05-29 James Y. Huang , Wenxuan Zhou , Fei Wang , Fred Morstatter , Sheng Zhang , Hoifung Poon , Muhao Chen

Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large…

Computation and Language · Computer Science 2025-02-18 Yu Wang , Ruihan Wu , Zexue He , Xiusi Chen , Julian McAuley

Unlearning in Large Language Models (LLMs) is essential for ensuring ethical and responsible AI use, especially in addressing privacy leak, bias, safety, and evolving regulations. Existing approaches to LLM unlearning often rely on retain…

Computation and Language · Computer Science 2024-10-16 Yaxuan Wang , Jiaheng Wei , Chris Yuhao Liu , Jinlong Pang , Quan Liu , Ankit Parag Shah , Yujia Bao , Yang Liu , Wei Wei

Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content. Existing jailbreaking defense methods have failed to address the fundamental issue that harmful knowledge resides within the…

Computation and Language · Computer Science 2024-07-04 Weikai Lu , Ziqian Zeng , Jianwei Wang , Zhengdong Lu , Zelin Chen , Huiping Zhuang , Cen Chen

Large language model unlearning has become a critical challenge in ensuring safety and controlled model behavior by removing undesired data-model influences from the pretrained model while preserving general utility. Significant recent…

Computation and Language · Computer Science 2025-04-17 Soumyadeep Pal , Changsheng Wang , James Diffenderfer , Bhavya Kailkhura , Sijia Liu

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

Machine Learning · Computer Science 2025-04-10 Xiaohua Feng , Yuyuan Li , Huwei Ji , Jiaming Zhang , Li Zhang , Tianyu Du , Chaochao Chen

In this work, we demonstrate that certain machine unlearning methods may fail under straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families using output-based, logit-based, and…

Cryptography and Security · Computer Science 2025-08-15 Yeonwoo Jang , Shariqah Hossain , Ashwin Sreevatsa , Diogo Cruz

A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and…

Computation and Language · Computer Science 2024-04-18 Christian Tomani , Kamalika Chaudhuri , Ivan Evtimov , Daniel Cremers , Mark Ibrahim

Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns. However, recent studies reveal a critical vulnerability:…

Computation and Language · Computer Science 2026-05-13 Zeguan Xiao , Xuanzhe Xu , Yun Chen , Yong Wang , Jian Yang , Yanqing Hu , Guanhua Chen

Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and item attributes. However, as privacy regulations tighten,…

Information Retrieval · Computer Science 2026-04-08 Ziheng Chen , Jiali Cheng , Zezhong Fan , Hadi Amiri , Yunzhi Yao , Xiangguo Sun , Yang Zhang

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

Computation and Language · Computer Science 2024-10-23 Chonghua Liao , Ruobing Xie , Xingwu Sun , Haowen Sun , Zhanhui Kang

With growing demands for privacy protection, security, and legal compliance (e.g., GDPR), machine unlearning has emerged as a critical technique for ensuring the controllability and regulatory alignment of machine learning models. However,…

Machine Learning · Computer Science 2026-04-08 Lulu Xue , Shengshan Hu , Wei Lu , Yan Shen , Dongxu Li , Peijin Guo , Ziqi Zhou , Minghui Li , Yanjun Zhang , Leo Yu Zhang

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Machine Learning · Computer Science 2026-02-02 Hsiang Hsu , Pradeep Niroula , Zichang He , Ivan Brugere , Freddy Lecue , Chun-Fu Chen