English
Related papers

Related papers: Towards Localized and Disentangled Knowledge Editi…

200 papers

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

Machine Learning · Computer Science 2025-05-27 Zexi Li , Xiangzhu Wang , William F. Shen , Meghdad Kurmanji , Xinchi Qiu , Dongqi Cai , Chao Wu , Nicholas D. Lane

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the…

Computation and Language · Computer Science 2025-06-11 Zeyu Leo Liu , Greg Durrett , Eunsol Choi

Model editing aims to correct outdated or erroneous knowledge in large models without costly retraining. Recent research discovered that the mid-layer representation of the subject's final token in a prompt has a strong influence on factual…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Qizhou Chen , Taolin Zhang , Chengyu Wang , Xiaofeng He , Dakan Wang , Tingting Liu

Understanding and continuously refining multimodal molecular knowledge is crucial for advancing biomedicine, chemistry, and materials science. Molecule language models (MoLMs) have become powerful tools in these domains, integrating…

Machine Learning · Computer Science 2025-12-01 Zhenyu Lei , Patrick Soga , Yaochen Zhu , Yinhan He , Yushun Dong , Jundong Li

Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated…

Computation and Language · Computer Science 2025-09-09 Changyue Wang , Weihang Su , Qingyao Ai , Yichen Tang , Yiqun Liu

Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned.…

Computation and Language · Computer Science 2022-10-27 Yifan Hou , Wenxiang Jiao , Meizhen Liu , Carl Allen , Zhaopeng Tu , Mrinmaya Sachan

Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing methods (KEs) that can change specific facts in LLMs with limited…

Computation and Language · Computer Science 2025-06-18 Paul Youssef , Zhixue Zhao , Daniel Braun , Jörg Schlötterer , Christin Seifert

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Shen Lin , Jing Lin , Junhao Dong , Piotr Koniusz , Li Xu

In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with prior approaches, we propose to eliminate prompt engineering…

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…

Computation and Language · Computer Science 2026-01-30 Xiaopeng Li , Shasha Li , Xi Wang , Shezheng Song , Bin Ji , Shangwen Wang , Jun Ma , Xiaodong Liu , Mina Liu , Jie Yu

Knowledge editing has emerged as an efficient technique for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there is a lack of effective measures to prevent the malicious…

Computation and Language · Computer Science 2025-05-27 Xiaopeng Li , Shasha Li , Shangwen Wang , Shezheng Song , Bin Ji , Huijun Liu , Jun Ma , Jie Yu

Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two…

Computation and Language · Computer Science 2024-10-10 Weichuan Wang , Zhaoyi Li , Defu Lian , Chen Ma , Linqi Song , Ying Wei

Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…

Computation and Language · Computer Science 2025-10-27 Fufang Wen , Shichang Zhang

Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and…

Computation and Language · Computer Science 2025-12-09 Yinjie Cheng , Paul Youssef , Christin Seifert , Jörg Schlötterer , Zhixue Zhao

Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this…

Computation and Language · Computer Science 2024-11-08 Jared Fernandez , Yonatan Bisk , Emma Strubell

Advances in multi-modal large language models (MLLMs) have inspired time series understanding and reasoning tasks, that enable natural language querying over time series, producing textual analyses of complex temporal dynamics. Recent…

Machine Learning · Computer Science 2026-02-05 Hang Ni , Weijia Zhang , Fei Wang , Zezhi Shao , Hao Liu

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

Learning disentangled representations, where distinct factors of variation are captured by independent latent variables, is a central goal in machine learning. The dominant approach has been the Variational Autoencoder (VAE) framework,…

Machine Learning · Computer Science 2025-10-15 Quentin Fruytier , Akshay Malhotra , Shahab Hamidi-Rad , Aditya Sant , Aryan Mokhtari , Sujay Sanghavi

Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified target fact robustly, but often overlooks its deductive…

Computation and Language · Computer Science 2025-11-13 Ruihan Wu , Chhavi Yadav , Russ Salakhutdinov , Kamalika Chaudhuri

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-remains challenging.…

Computation and Language · Computer Science 2026-01-13 Qitan Lv , Tianyu Liu , Qiaosheng Zhang , Xingcheng Xu , Chaochao Lu