CaKE：电路感知编辑赋能通用知识学习器

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

March 20, 2025

作者: Yunzhi Yao, Jizhan Fang, Jia-Chen Gu, Ningyu Zhang, Shumin Deng, Huajun Chen, Nanyun Peng

cs.AI

摘要

知识编辑（Knowledge Editing, KE）技术能够修正大型语言模型（LLMs）中过时或错误的信息。尽管现有的KE方法可以更新孤立的事实，但在将这些更新推广至依赖于修改后知识的多跳推理任务时却面临挑战。通过分析推理回路——即LLMs用于基于知识推断的神经路径，我们注意到当前局限于单层或少数几层的KE方法，如MEMIT和WISE，难以有效将更新信息融入这些推理路径。针对这一局限，我们提出了CaKE（Circuit-aware Knowledge Editing），一种新颖的方法，旨在更高效地将更新知识整合到LLMs中。CaKE利用基于回路分析精心策划的数据，强制模型使用修改后的知识，激励模型为新整合的知识构建适当的推理回路。实验结果显示，CaKE在相关推理任务中实现了更新知识更准确、一致的应用，相较于现有KE方法，在MQuAKE数据集上的多跳推理准确率平均提升了20%。我们已在https://github.com/zjunlp/CaKE发布了代码和数据。

English

Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they struggle to generalize these updates to multi-hop reasoning tasks that depend on the modified knowledge. Through an analysis of reasoning circuits -- the neural pathways LLMs use for knowledge-based inference, we observe that current layer-localized KE approaches, such as MEMIT and WISE, which edit only single or a few model layers, struggle to effectively incorporate updated information into these reasoning pathways. To address this limitation, we propose CaKE (Circuit-aware Knowledge Editing), a novel method that enables more effective integration of updated knowledge in LLMs. CaKE leverages strategically curated data, guided by our circuits-based analysis, that enforces the model to utilize the modified knowledge, stimulating the model to develop appropriate reasoning circuits for newly integrated knowledge. Experimental results show that CaKE enables more accurate and consistent use of updated knowledge across related reasoning tasks, leading to an average of 20% improvement in multi-hop reasoning accuracy on MQuAKE dataset compared to existing KE methods. We release the code and data in https://github.com/zjunlp/CaKE.