Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall tasks involving newly edited knowledge. In this paper,...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
18.10.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall tasks involving newly edited knowledge. In this paper, leveraging tools in mechanistic interpretability, we first identify that in multi-hop tasks, LLMs tend to retrieve implicit subject knowledge from deeper MLP layers, unlike single-hop tasks, which rely on earlier layers. This distinction explains the poor performance of current methods in multi-hop queries, as they primarily focus on editing shallow layers, leaving deeper layers unchanged. To address this, we propose IFMET, a novel locate-then-edit KE approach designed to edit both shallow and deep MLP layers. IFMET employs multi-hop editing prompts and supplementary sets to locate and modify knowledge across different reasoning stages. Experimental results demonstrate that IFMET significantly improves performance on multi-hop factual recall tasks, effectively overcoming the limitations of previous locate-then-edit methods. |
---|---|
ISSN: | 2331-8422 |