English
Related papers

Related papers: Edit Less, Achieve More: Dynamic Sparse Neuron Mas…

200 papers

Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is…

Computation and Language · Computer Science 2024-07-24 Xiou Ge , Ali Mousavi , Edouard Grave , Armand Joulin , Kun Qian , Benjamin Han , Mostafa Arefiyan , Yunyao Li

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra…

Computation and Language · Computer Science 2024-02-20 Zihao Lin , Mohammad Beigi , Hongxuan Li , Yufan Zhou , Yuxiang Zhang , Qifan Wang , Wenpeng Yin , Lifu Huang

Deep Neural networks (DNNs), extensively applied across diverse disciplines, are characterized by their integrated and monolithic architectures, setting them apart from conventional software systems. This architectural difference introduces…

Machine Learning · Computer Science 2025-07-29 Shide Zhou , Tianlin Li , Yihao Huang , Ling Shi , Kailong Wang , Yang Liu , Haoyu Wang

Although large language models (LLMs) excel in knowledge recall and reasoning, their static nature leads to outdated information as the real world evolves or when adapting to domain-specific knowledge, highlighting the need for effective…

Computation and Language · Computer Science 2025-04-02 Ruoxi Xu , Yunjie Ji , Boxi Cao , Yaojie Lu , Hongyu Lin , Xianpei Han , Ben He , Yingfei Sun , Xiangang Li , Le Sun

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Computation and Language · Computer Science 2025-12-25 Shariqah Hossain , Lalana Kagal

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

Computation and Language · Computer Science 2026-02-02 Ruilin Li , Yibin Wang , Wenhong Zhu , Chenglin Li , Jinghao Zhang , Chenliang Li , Junchi Yan , Jiaqi Wang

Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…

Computation and Language · Computer Science 2025-02-11 Paul Youssef , Zhixue Zhao , Christin Seifert , Jörg Schlötterer

Model editing, the process of efficiently modifying factual knowledge in pre-trained language models, is critical for maintaining their accuracy and relevance. However, existing editing methods often introduce unintended side effects,…

Computation and Language · Computer Science 2025-09-23 Tsung-Hsuan Pan , Chung-Chi Chen , Hen-Hsen Huang , Hsin-Hsi Chen

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

This study investigates the impact of localized updates to large language models (LLMs), specifically in the context of knowledge editing - a task aimed at incorporating or modifying specific facts without altering broader model…

Computation and Language · Computer Science 2025-02-27 Akshat Gupta , Christine Fang , Atahan Ozdemir , Maochuan Lu , Ahmed Alaa , Thomas Hartvigsen , Gopala Anumanchipalli

Knowledge-editing updates knowledge of large language models (LLMs) and contributes to the interpretability and application of LLMs. However, knowledge applying is context-consistent: LLMs can recall the same knowledge in different…

Computation and Language · Computer Science 2024-01-18 Youcheng Huang , Wenqiang Lei , Zheng Zhang , Jiancheng Lv , Shuicheng Yan

Recent work has showcased the powerful capability of large language models (LLMs) in recalling knowledge and reasoning. However, the reliability of LLMs in combining these two capabilities into reasoning through multi-hop facts has not been…

Computation and Language · Computer Science 2024-06-04 Tianjie Ju , Yijin Chen , Xinwei Yuan , Zhuosheng Zhang , Wei Du , Yubin Zheng , Gongshen Liu

Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated excellent multilingual capabilities, which can express the…

Computation and Language · Computer Science 2024-11-27 Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting…

Computation and Language · Computer Science 2025-01-15 Jiaang Li , Quan Wang , Zhongnan Wang , Yongdong Zhang , Zhendong Mao

Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper,…

Computation and Language · Computer Science 2024-09-26 Zeping Yu , Sophia Ananiadou

Large language models (LLMs) require continual knowledge updates to stay abreast of the ever-changing world facts, prompting the formulation of lifelong model editing task. While recent years have witnessed the development of various…

Computation and Language · Computer Science 2024-07-01 Renzhi Wang , Piji Li

Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full…

Computation and Language · Computer Science 2026-04-07 Sicheng Lyu , Yu Gu , Xinyu Wang , Jerry Huang , Sitao Luan , Yufei Cui , Xiao-Wen Chang , Peng Lu

Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful knowledge in LLMs, which allows such attacks to bypass…

Computation and Language · Computer Science 2025-05-27 Zesheng Shi , Yucheng Zhou , Jing Li

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing outdated knowledge in…

Computation and Language · Computer Science 2024-09-17 Baolong Bi , Shenghua Liu , Yiwei Wang , Lingrui Mei , Hongcheng Gao , Junfeng Fang , Xueqi Cheng