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

TL;DR

This paper introduces a biomedical question answering model that combines multi-hop reasoning, contextual retrieval, and question decomposition to improve accuracy and efficiency in complex medical queries, achieving high performance on a shared task dataset.

Contribution

The paper presents a novel model that effectively handles both direct and sequential biomedical questions using multi-source retrieval and in-context learning, advancing QA capabilities in medical domains.

Findings

Achieved an Exact Match score of 0.84 on MedHopQA dataset

Ranked second on the BioCreative IX leaderboard

Demonstrated effective multi-hop reasoning and context utilization

Abstract

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.