轻量级知识编辑框架，大幅提升多跳问答准确率与检索效率。
ALEX:A Light Editing-knowledge Extractor
- 分层记忆架构将知识更新聚类，降低检索复杂度
- 多跳问答准确率提升，搜索空间缩小超80%
- 适合需要高效知识更新的大型模型系统
大语言模型中的知识具有静态特性，难以适应动态信息，因此知识编辑成为关键任务。然而现有方法在可扩展性和检索效率方面面临挑战，尤其在处理需多步推理的复杂多跳问题时。本文提出轻量级知识编辑框架ALEX（A Light Editing-knowledge Extractor），其核心是分层记忆架构，将知识更新按语义聚类，使检索复杂度从线性O(N)降至高度可扩展的O(K+N/C)。同时集成推理查询生成（IQS）模块以弥合查询与事实间的语义鸿沟，并引入动态证据裁决（DEA）引擎，实现高效的两阶段检索。在MQUAKE基准上的实验表明，ALEX显著提升了多跳回答准确率（MultiHop-ACC）和推理路径可靠性（HopWise-ACC），搜索空间缩减超过80%，为构建可扩展、高效且精准的知识编辑系统提供了可行路径。
原文摘要 · Abstract (English)
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.
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。