用分步查询提升大模型对复杂时序问题的问答能力
The benefits of query-based KGQA systems for complex and temporal questions in LLM era
- 分阶段生成可执行查询，替代直接回答
- 在多跳和时序问答上显著优于直接生成
- 适合需要可解释推理的小模型应用
大语言模型在问答任务中表现优异，但在多跳推理和时序问题上仍存在困难。基于查询的知识图谱问答（KGQA）通过生成可执行查询而非直接答案，提供了一种模块化替代方案。本文提出一种针对WikiData的多阶段查询式KGQA框架，在复杂多跳和时序问答基准上均取得显著提升。通过泛化性和拒答性研究，验证了该方法在多跳与时序数据集上的鲁棒性。此外，引入基于思维链（CoT）的实体链接与谓词匹配新方法。结果表明，该多阶段查询式框架能有效提升小语言模型在多跳与时序问答中的性能。代码与数据见：https://github.com/ar2max/NLDB-KGQA-System
原文摘要 · Abstract (English)
Large language models excel in question-answering (QA) yet still struggle with multi-hop reasoning and temporal questions. Query-based knowledge graph QA (KGQA) offers a modular alternative by generating executable queries instead of direct answers. We explore multi-stage query-based framework for WikiData QA, proposing multi-stage approach that enhances performance on challenging multi-hop and temporal benchmarks. Through generalization and rejection studies, we evaluate robustness across multi-hop and temporal QA datasets. Additionally, we introduce a novel entity linking and predicate matching method using CoT reasoning. Our results demonstrate the potential of query-based multi-stage KGQA framework for improving multi-hop and temporal QA with small language models. Code and data: https://github.com/ar2max/NLDB-KGQA-System
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。