Event-based knowledge editing for deterministic knowledge propagation in large language models

The dynamic nature of real-world information necessitates knowledge editing (KE) in large language models (LLMs). This edited knowledge should propagate and facilitate the deduction of new information based on existing model knowledge. We define the existing related knowledge in a LLM serving as the origination of knowledge propagation as ``deduction anchors''. However, most of current KE approaches only operate on (subject, relation, object) triples. Both theoretically and empirically, we observe that this simplified setting often leads to uncertainty when determining the deduction anchors, causing low confidence in their responses. To mitigate this issue, we propose a novel task of event-based knowledge editing that pairs facts with event descriptions. This task manifests both as a closer simulation of real-world editing scenarios and a more logically sound setting, implicitly defining the deduction anchor and enabling LLMs to propagate knowledge confidently. We curate a new benchmark dataset evedit derived from the CounterFact dataset and validate its superiority in improving model confidence. Moreover, as we observe that the event-based setting is notably challenging for existing approaches, we propose a novel approach Self-Edit that showcases stronger performance, achieving 55.6\% consistency improvement while maintaining the naturalness of generation.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Liu, Jiateng

Contributors dc:contributor

• Ji, Heng

• Knowledge Editing
• Language Models

Statement dc:rights

• Copyright 2025 Jiateng Liu

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/129215

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F129215