ALEX:A Light Editing-knowledge Extractor

The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability and retrieval efficiency, particularly when handling complex, multi-hop questions that require multi-step reasoning. To address these challenges, this paper introduces ALEX (A Light Editing-knowledge Extractor), a lightweight knowledge editing framework. The core innovation of ALEX is its hierarchical memory architecture, which organizes knowledge updates (edits) into semantic clusters. This design fundamentally reduces retrieval complexity from a linear O(N) to a highly scalable O(K+N/C). Furthermore, the framework integrates an Inferential Query Synthesis (IQS) module to bridge the semantic gap between queries and facts, and a Dynamic Evidence Adjudication (DEA) engine that executes an efficient two-stage retrieval process. Experiments on the MQUAKE benchmark demonstrate that ALEX significantly improves both the accuracy of multi-hop answers (MultiHop-ACC) and the reliability of reasoning paths (HopWise-ACC). It also reduces the required search space by over 80%, presenting a promising path toward building scalable, efficient, and accurate knowledge editing systems.

Authors

• Minghu Wang College of Computer and Cyber Security, Hebei Normal University, Hebei 050024, China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security, Hebei 050024, China Hebei Provincial Key Laboratory of Network and Information Security, Hebei 050024, China
• ShuLiang Zhao College of Computer and Cyber Security, Hebei Normal University, Hebei 050024, China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security, Hebei 050024, China Hebei Provincial Key Laboratory of Network and Information Security, Hebei 050024, China
• Yuanyuan Zhao Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security, Hebei 050024, China Hebei Provincial Key Laboratory of Network and Information Security, Hebei 050024, China School of Mathematical Sciences, Hebei Normal University, Hebei 050024, China Dept of Information Engineering, Shijiazhuang College of Applied Technology, Hebei 050043, China
• Hongxia Xu College of Computer and Cyber Security, Hebei Normal University, Hebei 050024, China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security, Hebei 050024, China Hebei Provincial Key Laboratory of Network and Information Security, Hebei 050024, China

Keywords

No keywords are indexed for this paper.