QueryFlow 论文提出自适应查询演化的多跳图检索方法
QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution
一个改进多跳 RAG 检索的新方法，把查询和图上下文联动更新，四个多跳 QA 数据集上 Recall 和准确率都有明显提升，做 RAG 的可以看看。
QueryFlow 把多跳证据恢复视为证据表示与查询条件的耦合演化，通过循环方式将查询条件化的图上下文摘要整合进共享查询状态，控制后续传播的边界输入和关系特征。与固定查询的图检索器不同，它会根据累积的关系上下文调整查询条件。在四个多跳 QA 数据集上，QueryFlow 的 macro R@10、FR@10 和 LLM-Acc 相比代表性基线分别提升 4.98、8.40 和 8.0 个百分点。论文已发布在 arXiv（编号 2611.04625）。
QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution
Multi-hop retrieval-augmented generation (RAG) supports Web information seeking and fact verification by recovering complementary evidence across related pages within a limited retrieval budget. Scoring evidence independently against the original question can miss supporting units whose relevance emerges through intermediate facts. Iterative retrieval incorporates these facts into subsequent queries, while graph retrieval explicitly models relations among evidence units. Yet fixed-query graph retrievers update entity representations without adapting the query condition to accumulated relational context. We view multi-hop evidence recovery as the coupled evolution of evidence representations and query conditions, with accumulated context informing both what the retriever represents and how it searches for complementary evidence. QueryFlow realizes this perspective by recurrently integrating query-conditioned summaries of graph context into a shared query state, which controls boundary inputs and relation features for subsequent propagation. Across four representative multi-hop question answering (QA) datasets, QueryFlow achieves macro Recall@10 (R@10), Full Recall@10 (FR@10), and LLM-Acc gains of 4.98, 8.40, and 8.0 percentage points over representative baselines, respectively.