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

Liu, Jiateng

Permalink

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

Description

Title

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

Author(s)

Liu, Jiateng

Issue Date

2025-04-17

Director of Research (if dissertation) or Advisor (if thesis)

Ji, Heng

Department of Study

Siebel School Comp & Data Sci

Discipline

Computer Science

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

Knowledge Editing, Language Models

Abstract

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.

Graduation Semester

2025-05

Type of Resource

Thesis

Handle URL

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

Copyright and License Information

Copyright 2025 Jiateng Liu

Owning Collections