让检索过程像推理一样找路径，提升复杂问答准确率。
DOTRAG: Retrieval-Time Reasoning Along Paths
- 用查询条件动态生成约束，引导图谱搜索路径
- 在MetaQA和UltraDomain上达到当前最优，多跳任务提升明显
- 无需训练，适合需要精准关系推理的场景
图检索增强生成（GraphRAG）普遍采用先检索后推理的范式，依赖启发式方法获取上下文，难以适应复杂多跳任务所需的查询特定逻辑，常引入无关信息或遗漏正确关系路径。本文提出DotRAG，一种无需训练的GraphRAG框架，将检索重新定义为路径上的推理过程。通过生成查询相关的约束条件，引导图谱探索、剪枝无关区域，并迭代发现关系路径，无需显式的逐步推理链。引入思想分解（Division of Thought, DOT），将检索拆分为局部搜索空间，根据查询自适应调整搜索策略。DotRAG在MetaQA和UltraDomain数据集上实现当前最优性能，在多跳任务中表现一致提升，验证了推理引导检索的有效性。
原文摘要 · Abstract (English)
Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for complex multi-hop tasks, often accumulating irrelevant context or missing correct relational paths. We propose DotRAG, a training-free GraphRAG framework that reformulates retrieval as a reasoning process over paths. Our approach generates query-conditioned constraints that guide graph exploration, prune irrelevant regions, and iteratively discover relational paths without relying on explicit step-by-step reasoning chains. We introduce Division of Thought (DOT), an abstraction that decomposes retrieval into localized search spaces and adapts the search strategy to each query. DotRAG achieves SOTA performance on MetaQA and UltraDomain, with consistent gains on multi-hop tasks, demonstrating the effectiveness of reasoning-guided retrieval.
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。