English
Related papers

Related papers: LLM Unlearning with LLM Beliefs

200 papers

How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense…

Computation and Language · Computer Science 2023-10-10 Tian Jin , Nolan Clement , Xin Dong , Vaishnavh Nagarajan , Michael Carbin , Jonathan Ragan-Kelley , Gintare Karolina Dziugaite

Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the…

Computation and Language · Computer Science 2025-01-07 Zibin Pan , Shuwen Zhang , Yuesheng Zheng , Chi Li , Yuheng Cheng , Junhua Zhao

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data…

Computation and Language · Computer Science 2025-06-03 Jiahui Geng , Qing Li , Herbert Woisetschlaeger , Zongxiong Chen , Fengyu Cai , Yuxia Wang , Preslav Nakov , Hans-Arno Jacobsen , Fakhri Karray

Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. Our study here searches through LLMs' cognitive abilities and confidence dynamics. We dive deep into understanding the alignment…

Computation and Language · Computer Science 2023-09-29 Aniket Kumar Singh , Suman Devkota , Bishal Lamichhane , Uttam Dhakal , Chandra Dhakal

Large language models (LLMs) require iterative updates to address the outdated information problem, where LLM unlearning offers an approach for selective removal. However, mainstream unlearning methods primarily rely on fine-tuning…

Computation and Language · Computer Science 2025-09-29 Miao Yu , Liang Lin , Guibin Zhang , Xinfeng Li , Junfeng Fang , Xingrui Yu , Ivor Tsang , Ningyu Zhang , Kun Wang , Yang Wang

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

Machine Learning · Computer Science 2025-10-23 Xiaoyu Wu , Yifei Pang , Terrance Liu , Zhiwei Steven Wu

Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these problems, where LLMs' focus shifts towards newly generated tokens and away from the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xu Liu , Guikun Chen , Wenguan Wang

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…

Artificial Intelligence · Computer Science 2025-04-21 Gabriel Freedman , Francesca Toni

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…

Computation and Language · Computer Science 2026-05-15 Borisiuk Anna , Andrey Savchenko , Alexander Panchenko , Elena Tutubalina

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Computation and Language · Computer Science 2022-03-16 Adam Gleave , Geoffrey Irving

Large language models learn and continually learn through the accumulation of gradient-based updates, but how individual pieces of new information affect existing knowledge, leading to both beneficial generalization and problematic…

Computation and Language · Computer Science 2025-04-15 Chen Sun , Renat Aksitov , Andrey Zhmoginov , Nolan Andrew Miller , Max Vladymyrov , Ulrich Rueckert , Been Kim , Mark Sandler

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

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

Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risks, they remain vulnerable to "relearning" during subsequent…

Machine Learning · Computer Science 2026-03-05 Nakyeong Yang , Dong-Kyum Kim , Jea Kwon , Minsung Kim , Kyomin Jung , Meeyoung Cha

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Computation and Language · Computer Science 2023-06-23 Yanrui Du , Jing Yan , Yan Chen , Jing Liu , Sendong Zhao , Qiaoqiao She , Hua Wu , Haifeng Wang , Bing Qin

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Computation and Language · Computer Science 2025-12-05 Purbesh Mitra , Sennur Ulukus

Natural language generation (NLG) is one of the most impactful fields in NLP, and recent years have witnessed its evolution brought about by large language models (LLMs). As the key instrument for writing assistance applications, they are…

Computation and Language · Computer Science 2023-06-07 Minghui Zhang , Alex Sokolov , Weixin Cai , Si-Qing Chen

Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are crucial to remove undesirable responses, ensuring legal and…

Machine Learning · Computer Science 2025-02-27 Qizhou Wang , Jin Peng Zhou , Zhanke Zhou , Saebyeol Shin , Bo Han , Kilian Q. Weinberger

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than…

Artificial Intelligence · Computer Science 2025-10-03 Phuc Minh Nguyen , Chinh D. La , Duy M. H. Nguyen , Nitesh V. Chawla , Binh T. Nguyen , Khoa D. Doan