EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval

arXiv:2608.13006v1 Announce Type: new Abstract: Multi-hop retrieval must recover passages that provide sufficient evidence together. An initial passage often resolves an entity or relation implicit in the question, making the missing evidence easier to describe only after retrieval begins. Graph retrieval improves access to related evidence through stored corpus structure, but its retrieval signal is commonly derived from the original question. Complementary evidence must then be reached through stored relations even when an observed passage provides a more direct semantic cue. We introduce EviReform, which separates revising the retrieval request from aggregating evidence in the graph. Retrieved source passages formulate residual queries for the unresolved information need. The original and residual retrieval signals are normalized separately, combined, and propagated between propositions that share entities. On 2WikiMultiHopQA, HotpotQA, and MuSiQue, EviReform exceeds the strongest baseline by up to 5.59 Recall@5 points and 4.50 F1 points. These results show that observed evidence can guide graph retrieval toward the part of a supporting chain left underspecified by the original question. Code is available at https://github.com/XrazyMee/EviReform.

Related

• Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
• TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
• Grounding LLM Reasoning under Incomplete Graph Evidence
• Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration

Source: arXiv cs.CL | 2026-08-14