CUNI-a at ArchEHR-QA 2025: Do we need Giant LLMs for Clinical QA?

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511614" target="_blank" >RIV/00216208:11320/25:10511614 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2025.bionlp-share.4/" target="_blank" >https://aclanthology.org/2025.bionlp-share.4/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.bionlp-share.4" target="_blank" >10.18653/v1/2025.bionlp-share.4</a>

Result language

angličtina

Original language name

CUNI-a at ArchEHR-QA 2025: Do we need Giant LLMs for Clinical QA?

Original language description

In this paper, we present our submission to the ArchEHR-QA 2025 shared task, which focuses on answering patient questions based on excerpts from electronic health record (EHR) discharge summaries. Our approach identifies essential sentences relevant to a patient&apos;s question using a combination of few-shot inference with the Med42-8B model, cosine similarity over clinical term embeddings, and the MedCPT cross-encoder relevance model. Then, concise answers are generated on the basis of these selected sentences. Despite not relying on large language models (LLMs) with tens of billions of parameters, our method achieves competitive results, demonstrating the potential of resource-efficient solutions for clinical NLP applications.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks)

ISBN

979-8-89176-276-3

ISSN

—

e-ISSN

—

Number of pages

14

Pages from-to

27-40

Publisher name

Association for Computational Linguistics

Place of publication

Kerrville, TX, USA

Event location

Wien, Austria

Event date

Aug 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—