UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Quoc-An, Vu, Thi-Minh-Thu, Nguyen, Bich-Dat, Tran, Dinh-Quang-Minh, Le, Hoang-Quynh
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909987442262016
author Nguyen, Quoc-An
Vu, Thi-Minh-Thu
Nguyen, Bich-Dat
Tran, Dinh-Quang-Minh
Le, Hoang-Quynh
author_facet Nguyen, Quoc-An
Vu, Thi-Minh-Thu
Nguyen, Bich-Dat
Tran, Dinh-Quang-Minh
Le, Hoang-Quynh
contents Biomedical Question Answering systems play a critical role in processing complex medical queries, yet they often struggle with the intricate nature of medical data and the demand for multi-hop reasoning. In this paper, we propose a model designed to effectively address both direct and sequential questions. While sequential questions are decomposed into a chain of sub-questions to perform reasoning across a chain of steps, direct questions are processed directly to ensure efficiency and minimise processing overhead. Additionally, we leverage multi-source information retrieval and in-context learning to provide rich, relevant context for generating answers. We evaluated our model on the BioCreative IX - MedHopQA Shared Task datasets. Our approach achieves an Exact Match score of 0.84, ranking second on the current leaderboard. These results highlight the model's capability to meet the challenges of Biomedical Question Answering, offering a versatile solution for advancing medical research and practice.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06974
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval
Nguyen, Quoc-An
Vu, Thi-Minh-Thu
Nguyen, Bich-Dat
Tran, Dinh-Quang-Minh
Le, Hoang-Quynh
Computation and Language
Biomedical Question Answering systems play a critical role in processing complex medical queries, yet they often struggle with the intricate nature of medical data and the demand for multi-hop reasoning. In this paper, we propose a model designed to effectively address both direct and sequential questions. While sequential questions are decomposed into a chain of sub-questions to perform reasoning across a chain of steps, direct questions are processed directly to ensure efficiency and minimise processing overhead. Additionally, we leverage multi-source information retrieval and in-context learning to provide rich, relevant context for generating answers. We evaluated our model on the BioCreative IX - MedHopQA Shared Task datasets. Our approach achieves an Exact Match score of 0.84, ranking second on the current leaderboard. These results highlight the model's capability to meet the challenges of Biomedical Question Answering, offering a versatile solution for advancing medical research and practice.
title UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval
topic Computation and Language
url https://arxiv.org/abs/2601.06974