English
Related papers

Related papers: Mechanistic Circuit-Based Knowledge Editing in Lar…

200 papers

Recent knowledge editing methods have primarily focused on modifying structured knowledge in large language models. However, this task setting overlooks the fact that a significant portion of real-world knowledge is stored in an…

Computation and Language · Computer Science 2025-02-26 Jingcheng Deng , Zihao Wei , Liang Pang , Hanxing Ding , Huawei Shen , Xueqi Cheng

Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black boxes and relies on…

Artificial Intelligence · Computer Science 2026-03-17 Yuhuan Liu , Haitian Zhong , Xinyuan Xia , Qiang Liu , Shu Wu , Liang Wang

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

Large language models (LLMs) have recently transformed both the academic and industrial landscapes due to their remarkable capacity to understand, analyze, and generate texts based on their vast knowledge and reasoning ability.…

Computation and Language · Computer Science 2024-09-23 Song Wang , Yaochen Zhu , Haochen Liu , Zaiyi Zheng , Chen Chen , Jundong Li

Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limited set of related or neighboring knowledge. While effective, such evaluations remain…

Computation and Language · Computer Science 2026-05-12 Shuainan Liu , Xuanang Chen , Ben He , Le Sun

Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple chains are sampled and aggregated through a…

Computation and Language · Computer Science 2024-08-05 Ori Yoran , Tomer Wolfson , Ben Bogin , Uri Katz , Daniel Deutch , Jonathan Berant

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…

Computation and Language · Computer Science 2025-05-20 Jiakuan Xie , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of…

Artificial Intelligence · Computer Science 2026-04-22 Dahyun Jung , Jaewook Lee , Heuiseok Lim

Large language models (LLMs) demonstrate strong reasoning abilities when prompted to generate chain-of-thought (CoT) explanations alongside answers. However, previous research on evaluating LLMs has solely focused on answer accuracy,…

Computation and Language · Computer Science 2024-06-21 Minh-Vuong Nguyen , Linhao Luo , Fatemeh Shiri , Dinh Phung , Yuan-Fang Li , Thuy-Trang Vu , Gholamreza Haffari

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Computation and Language · Computer Science 2023-11-07 Zeming Chen , Gail Weiss , Eric Mitchell , Asli Celikyilmaz , Antoine Bosselut

Knowledge editing aims to update outdated information in Large Language Models (LLMs). A representative line of study is locate-then-edit methods, which typically employ causal tracing to identify the modules responsible for recalling…

Computation and Language · Computer Science 2025-03-18 Haowen Pan , Xiaozhi Wang , Yixin Cao , Zenglin Shi , Xun Yang , Juanzi Li , Meng Wang

Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it's contextually inappropriate. To address this…

Artificial Intelligence · Computer Science 2025-05-27 Haitian Zhong , Yuhuan Liu , Ziyang Xu , Guofan Liu , Qiang Liu , Shu Wu , Zhe Zhao , Liang Wang , Tieniu Tan

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language…

Computation and Language · Computer Science 2024-10-28 Xinbei Ma , Tianjie Ju , Jiyang Qiu , Zhuosheng Zhang , Hai Zhao , Lifeng Liu , Yulong Wang

Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they…

Machine Learning · Computer Science 2025-08-07 Xin Liu , Qiyang Song , Shaowen Xu , Kerou Zhou , Wenbo Jiang , Xiaoqi Jia , Weijuan Zhang , Heqing Huang , Yakai Li

Knowledge stored in large language models requires timely updates to reflect the dynamic nature of real-world information. To update the knowledge, most knowledge editing methods focus on the low layers, since recent probes into the…

Computation and Language · Computer Science 2024-12-25 Wenhang Shi , Yiren Chen , Shuqing Bian , Xinyi Zhang , Zhe Zhao , Pengfei Hu , Wei Lu , Xiaoyong Du

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive…

Computation and Language · Computer Science 2024-06-18 Che Zhang , Zhenyang Xiao , Chengcheng Han , Yixin Lian , Yuejian Fang

Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and…

Artificial Intelligence · Computer Science 2025-10-14 Olivia Peiyu Wang , Tashvi Bansal , Ryan Bai , Emily M. Chui , Leilani H. Gilpin

The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability…

Artificial Intelligence · Computer Science 2025-11-19 Minghu Wang , Shuliang Zhao , Yuanyuan Zhao , Hongxia Xu

Accurately answering complex questions has consistently been a significant challenge for Large Language Models (LLMs). To address this, this paper proposes a multi-hop question decomposition method for complex questions, building upon…

Computation and Language · Computer Science 2025-09-08 Zucheng Liang , Wenxin Wei , Kaijie Zhang , Hongyi Chen

Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions…

Computation and Language · Computer Science 2024-04-02 Keyuan Cheng , Gang Lin , Haoyang Fei , Yuxuan zhai , Lu Yu , Muhammad Asif Ali , Lijie Hu , Di Wang
‹ Prev 1 4 5 6 7 8 10 Next ›