Work

RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models

Year: 2025

Type: conference-paper

Abstract: Knowledge editing emerges as a promising approach for updating target knowledge in Large Language Models (LLMs) in a timely manner, thereby preventing undesirable behaviors stemming from outdated, inaccurate, or incomplete knowledge.However, existing methods mainly focus on instance-level editing, which is prone to over-editing risk featuring knowledge degradation and general ability deterioration, due to redundant instance-specific modifications for knowledge.To mitigate the over-editing risk, we explore the rule-level editing problem that avoids case-by-case modification by generalizing rule-level knowledge to update rule-derived instances.We further construct a benchmark called RuleEdit for systematic evaluation on rule-level editing.Moreover, we propose a Rule-Transfer Editing (RTE) method to facilitate effective updates and generalizations of rule-level knowledge in LLMs.Experimental results highlight our significant improvements, with the enhancements of 28.1% in portability and 8.1% in average performance over the best-performing baselines for LLaMA-2-7B on RU LE mix .

DOI: 10.18653/v1/2025.findings-acl.164

Authors: Bihan Zhou, HaoPeng Ren, Li Yuan, Yi Cai, Liuwen Cao, Zikun Deng

Institutions: Ministry of Education of the People's Republic of China, South China University of Technology, Hong Kong Polytechnic University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province

Awards: G3621338742, G453967609

OpenAlex ID: W4412888750