Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Colelough, Brandon, Bartels, Davis, Demner-Fushman, Dina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913914722189312
author Colelough, Brandon
Bartels, Davis
Demner-Fushman, Dina
author_facet Colelough, Brandon
Bartels, Davis
Demner-Fushman, Dina
contents In this paper, we present an overview of ClinIQLink, a shared task, collocated with the 24th BioNLP workshop at ACL 2025, designed to stress-test large language models (LLMs) on medically-oriented question answering aimed at the level of a General Practitioner. The challenge supplies 4,978 expert-verified, medical source-grounded question-answer pairs that cover seven formats: true/false, multiple choice, unordered list, short answer, short-inverse, multi-hop, and multi-hop-inverse. Participating systems, bundled in Docker or Apptainer images, are executed on the CodaBench platform or the University of Maryland's Zaratan cluster. An automated harness (Task 1) scores closed-ended items by exact match and open-ended items with a three-tier embedding metric. A subsequent physician panel (Task 2) audits the top model responses.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering
Colelough, Brandon
Bartels, Davis
Demner-Fushman, Dina
Computation and Language
Artificial Intelligence
Information Retrieval
I.2.7
In this paper, we present an overview of ClinIQLink, a shared task, collocated with the 24th BioNLP workshop at ACL 2025, designed to stress-test large language models (LLMs) on medically-oriented question answering aimed at the level of a General Practitioner. The challenge supplies 4,978 expert-verified, medical source-grounded question-answer pairs that cover seven formats: true/false, multiple choice, unordered list, short answer, short-inverse, multi-hop, and multi-hop-inverse. Participating systems, bundled in Docker or Apptainer images, are executed on the CodaBench platform or the University of Maryland's Zaratan cluster. An automated harness (Task 1) scores closed-ended items by exact match and open-ended items with a three-tier embedding metric. A subsequent physician panel (Task 2) audits the top model responses.
title Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering
topic Computation and Language
Artificial Intelligence
Information Retrieval
I.2.7
url https://arxiv.org/abs/2506.21597