ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality

TL;DR

This paper introduces a two-step divide and conquer approach for patient question answering in clinical texts, emphasizing sentence extraction and answer generation without external knowledge, achieving top factuality scores.

Contribution

It proposes a novel two-step method that improves factuality in patient question answering by focusing on sentence extraction and answer generation without external data.

Findings

Re-ranker based two-step system performs best

Achieved an overall score of 0.44

Ranked 8th out of 30 on the leaderboard

Abstract

This work presents three different approaches to address the ArchEHR-QA 2025 Shared Task on automated patient question answering. We introduce an end-to-end prompt-based baseline and two two-step methods to divide the task, without utilizing any external knowledge. Both two step approaches first extract essential sentences from the clinical text, by prompt or similarity ranking, and then generate the final answer from these notes. Results indicate that the re-ranker based two-step system performs best, highlighting the importance of selecting the right approach for each subtask. Our best run achieved an overall score of 0.44, ranking 8th out of 30 on the leaderboard, securing the top position in overall factuality.