提出评估智能体图检索生成中引用可信度的新标准，强调溯源路径的重要性。
Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
- 将引用可信度视为遍历轨迹的整体问题，不仅看引用实体，还看未引用的路径信息。
- 实验证明删除引用实体会显著改变答案并降低准确率，但未引用的上下文也影响结果。
- 适合关注大模型推理可解释性与知识溯源的研究者或开发者。
检索增强生成可通过外部证据提升答案真实性，但智能体图检索增强生成（Agentic GraphRAG）使引用可信度的定义变得复杂。在该系统中，智能体在生成答案前先探索知识图谱，并仅返回少量引用。本文将引用可信度建模为轨迹层面的问题：最终引用不仅需支持答案，还需反映图遍历过程、结构及已访问但未引用的实体可能产生的影响。通过受控消融实验，我们对比了隔离、移除和遮蔽引用与未引用图实体的影响。结果表明，引用证据通常不可或缺，移除它们会显著改变答案并降低准确率。然而，引用并非充分条件，因为准确答案也可能依赖未引用的遍历上下文和周围图结构。这些发现提示，在智能体图检索增强生成中，引用评估应从单纯源支持转向对更广泛检索轨迹的溯源分析。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for citations to be faithful. In these systems, an agent explores a knowledge graph before producing an answer and a small set of citations. We frame citation faithfulness as a trajectory-level problem: final citations should not only support the answer, but also account for the graph traversal, structure, and visited-but-uncited entities that may influence it. Through controlled ablation experiments, we compare the effects of isolating, removing, and masking cited and uncited graph entities. Our results show that cited evidence is often necessary, as removing it substantially changes answers and reduces accuracy. However, citations are not sufficient, because accurate answers can also depend on uncited traversal context and surrounding graph structure. These findings suggest that citation evaluation in Agentic GraphRAG should move beyond source support toward provenance over the broader retrieval trajectory.
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。