ALEX:A Light Editing-knowledge Extractor

TL;DR

ALEX is a lightweight, scalable knowledge editing framework for LLMs that enhances multi-hop reasoning accuracy and efficiency through hierarchical memory and novel retrieval modules.

Contribution

Introduces ALEX, a hierarchical memory architecture with IQS and DEA modules, improving scalability and accuracy in knowledge editing for complex multi-hop questions.

Findings

Significantly improves multi-hop answer accuracy.

Reduces search space by over 80%.

Enhances reasoning path reliability.

Abstract

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.