Health AI Central
Peer-Reviewed Publication
Database (Oxford)2026;2026January 15, 2026Journal Article

Ensemble multi-retrieval methodologies with reasoning model decision in multi-step biomedical QA.

Jongmyung Jung1, Hyeongsoon Hwang1,2, Yein Park1,2, Minju Song1, Jaehoon Yun2,3, Hyeon Hwang1, Sanghoon Lee1,2, Jiwoong Sohn4, Jaewoo Kang1,2
1Department of Computer Science and Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.
2AIGEN Sciences, 58 Wangsimni-ro, Seongdong-gu, Seoul, 04778, Republic of Korea.
3College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea.
4Department of Biosystems Science and Engineering, ETH Zurich, Klingelbergstrasse 48, Basel, 4056, Switzerland.
PubMed PMC DOI PDF

Abstract

Robust and trustworthy biomedical question answering (QA) remains a critical challenge for large language models (LLMs), especially in complex domains such as rare diseases, where information is fragmented across multiple sources. MedHopQA 2025 benchmark introduces 10 000 multi-step reasoning questions curated from Wikipedia, requiring systems to extract, connect, and synthesize biomedical knowled…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.