AI RESEARCH
Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA
arXiv CS.LG
•
ArXi:2603.28886v1 Announce Type: cross Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores have different distributions and are not directly comparable. We study this as a score calibration problem for heterogeneous retrieval fusion in multi-hop question answering. Our method, PhaseGraph, maps vector and graph scores to a common unit-free scale using percentile-rank normalization (PIT) before fusion, enabling stable combination without discarding magnitude information.