QueryFlow improves multi-hop evidence search with adaptive queries

QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution

Information RetrievalArtificial Intelligence

Summary

Finding information from multiple related sources can be hard because sometimes clues only make sense when combined. The authors show that treating the search question as something that changes as new facts appear helps find better evidence. Their approach, QueryFlow, updates both the question and the evidence connections step-by-step to find more helpful pages. This method worked better than others on several question answering tests, helping large language models answer more accurately.

What this means in practice

  • For web search engineers: Improve search engines to find supporting facts across multiple web pages for complex questions using adaptive query updates.
  • For fact-checking teams: Enhance fact verification tools to combine evidence progressively by updating queries with intermediate findings.

Authors

Manzong Huang, Chenyang Bu, Yi He, Jiapu Wang, Xindong Wu

Abstract

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.