针对大模型多跳事实召回难题，提出双层编辑方法提升准确率
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
- 通过分析深层MLP层知识存储机制，定位多跳推理中关键信息
- 在多跳任务上准确率提升42.3%，显著优于现有方法
- 适合需要精准知识更新的复杂问答系统研发者
定位-编辑范式在大语言模型知识编辑中展现出巨大潜力。尽管现有方法在单跳事实召回任务中表现良好，但在涉及新编辑知识的多跳任务中持续表现不佳。本文利用机制可解释性工具发现：在多跳任务中，大模型倾向于从深层MLP层检索包含隐含主语的信息，而单跳任务则依赖浅层。这一差异解释了当前方法在多跳查询中表现差的原因——它们主要使用单跳编辑提示修改浅层，忽略深层变化。为此，我们提出IFMET，一种新型定位-编辑知识编辑方法，可同时编辑浅层与深层MLP层。除单跳编辑提示外，IFMET还引入多跳编辑提示，以定位并修改推理不同阶段的知识。实验结果表明，IFMET在多跳事实召回任务上显著提升性能，克服了以往定位-编辑方法的局限。
原文摘要 · Abstract (English)
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 knowledge with implicit subject information from deeper MLP layers, unlike single-hop tasks, which rely on shallow layers. This distinction explains the poor performance of current methods in multi-hop queries, as they primarily focus on editing shallow layers with single-hop edit prompts, 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. Beyond single-hop editing prompts, IFMET further incorporates multi-hop editing prompts to locate and modify knowledge across different stages of reasoning. Experimental results demonstrate that IFMET significantly improves performance on multi-hop factual recall tasks, overcoming the limitations of previous locate-then-edit methods
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。