Cost-Pragmatic Quality Gating and Selection-Fusion Multi-Model Combiners for BioASQ Phases A+ and B
arXiv cs.CL2w4 min read
arXiv:2607.13551v1 Announce Type: new Abstract: We describe our BioASQ Task 14B 2026 system. The work centers on two design decisions: how aggressively to re-retrieve when first-stage retrieval is weak, and how to combine multiple language-model answers. Retrieval unions two parallel pipelines - a hybrid first stage (dense BGE + BM25 + RRF, reaching R@200 = 99.3% on the BioASQ-13b historical archive) and an agent-driven pipeline that decomposes the question over PubMed, Europe PMC, and iCite - with a BGE cross-encoder quality gate flagging weakly-supported questions for selective re-retrieval.