用记忆模块分离查询与工具调用，提升大模型问答可读性
Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning
- 构建显式查询记忆模块，分离工具调用与知识推理
- 在WebQSP和CWQ上达到当前最佳性能
- 适合需要可解释性推理的KGQA系统研究者
大型语言模型（LLMs）在知识图谱问答（KGQA）任务中表现卓越，通过规划与知识图谱交互实现答案生成。然而，现有方法常混淆工具使用与知识推理，导致输出可读性差，并引发幻觉式工具调用，阻碍了KGQA的发展。为此，我们提出基于记忆增强的查询重构方法（MemQ），通过构建由大模型自建的查询记忆模块，将大模型与工具调用任务解耦。该方法利用显式描述的查询记忆，支持自然语言推理与记忆增强的查询重构，同时设计高效可读的推理机制，显著提升大模型在KGQA中的推理能力。实验表明，MemQ在WebQSP和CWQ两大主流基准上均取得当前最优性能。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved remarkable performance on knowledge graph question answering (KGQA) tasks by planning and interacting with knowledge graphs. However, existing methods often confuse tool utilization with knowledge reasoning, harming readability of model outputs and giving rise to hallucinatory tool invocations, which hinder the advancement of KGQA. To address this issue, we propose Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning (MemQ) to decouple LLM from tool invocation tasks using LLM-built query memory. By establishing a memory module with explicit descriptions of query statements, the proposed MemQ facilitates the KGQA process with natural language reasoning and memory-augmented query reconstruction. Meanwhile, we design an effective and readable reasoning to enhance the LLM's reasoning capability in KGQA. Experimental results that MemQ achieves state-of-the-art performance on widely used benchmarks WebQSP and CWQ.
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。