无需知识图谱结构即可用自然语言问问题并生成查询。
KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation
- 通过思考-行动-观察循环动态发现图结构和语义
- 在四个基准上提升F1约8点，成本与时间降22%
- 仅需轻量级类索引，适合真实世界数据接口
面向特定领域知识图谱的问答任务（KGQA）在缺乏正式本体和标注文本-SPARQL对的情况下仍具挑战性。本文提出KGVoyager，一种不依赖知识图谱的代理式架构，仅需底层图的查询端点即可从自然语言问题生成SPARQL查询。该方法利用思考-行动-观察循环，结合搜索、探索与执行工具，动态映射术语到图中IRI，揭示图结构，并通过执行反馈优化查询，全程无需预设本体或示例。相比现有最优方案，KGVoyager仅需轻量级类索引，适用范围更广。在四个基准测试中，其F1得分平均提升约8个百分点，同时降低约22%的成本与运行时间。
原文摘要 · Abstract (English)
Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific settings, where formal ontologies and curated text-SPARQL pairs are often unavailable. We present KGVoyager, a KG-agnostic agentic architecture that generates SPARQL queries from natural language questions by dynamically discovering graph structure and semantics, requiring only a query endpoint of the underlying graph. Using a think-act-observe loop with search, exploration, and execution tools, KGVoyager maps terms to graph IRIs, uncovers structure, and refines queries through execution feedback - all without pre-existing ontologies or examples. Unlike the prior state of the art, KGVoyager requires only a lightweight class index which renders it applicable for far more real-world endpoints. Across four benchmarks, KGVoyager improves F1 by ~8 points while cutting cost and runtime by ~22% each.
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。