用命题图遍历提升复杂问答能力，兼顾事实精度与结构连通性。
A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphs
- 构建命题-实体-段落异构图，融合细粒度事实与图结构连接
- 通过迭代建议-选择循环实现查询感知的图遍历，准确率显著提升
- 适合需要多跳推理和高精度事实检索的复杂问答场景
基于分块的标准RAG在简单事实检索上表现良好，但在复杂多跳查询上因缺乏结构连通性而失效。现有混合检索与推理的方法常缺乏全局语料意识，而基于知识图谱的RAG虽在多跳任务中表现优异，却在面向事实的单跳查询上效果不佳。为此，我们提出新型RAG框架ToPG（命题图遍历）。ToPG将知识库建模为命题、实体与段落构成的异构图，结合命题的细粒度事实密度与图结构的连通性。通过迭代式建议-选择循环：建议阶段实现查询感知的图遍历，选择阶段利用大模型反馈剔除无关命题并引导下一轮迭代。在三个不同QA任务（简单、复杂、抽象问答）上的评估表明，ToPG在准确率与生成质量等指标上均表现优异。结果证明，查询感知的图遍历与细粒度事实结合是高效结构化RAG系统的关键。
原文摘要 · Abstract (English)
Standard RAG pipelines based on chunking excel at simple factual retrieval but fail on complex multi-hop queries due to a lack of structural connectivity. Conversely, initial strategies that interleave retrieval with reasoning often lack global corpus awareness, while Knowledge Graph (KG)-based RAG performs strongly on complex multi-hop tasks but suffers on fact-oriented single-hop queries. To bridge this gap, we propose a novel RAG framework: ToPG (Traversal over Proposition Graphs). ToPG models its knowledge base as a heterogeneous graph of propositions, entities, and passages, effectively combining the granular fact density of propositions with graph connectivity. We leverage this structure using iterative Suggestion-Selection cycles, where the Suggestion phase enables a query-aware traversal of the graph, and the Selection phase provides LLM feedback to prune irrelevant propositions and seed the next iteration. Evaluated on three distinct QA tasks (Simple, Complex, and Abstract QA), ToPG demonstrates strong performance across both accuracy- and quality-based metrics. Overall, ToPG shows that query-aware graph traversal combined with factual granularity is a critical component for efficient structured RAG systems. ToPG is available at https://github.com/idiap/ToPG.
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。