SubmissionNumber#=%=#63
FinalPaperTitle#=%=#Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering
ShortPaperTitle#=%=#
NumberOfPages#=%=#10
CopyrightSigned#=%=#brandon C. colelough
JobTitle#==#
Organization#==#
Abstract#==#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.
Author{1}{Firstname}#=%=#brandon C.
Author{1}{Lastname}#=%=#colelough
Author{1}{Username}#=%=#brandon.colelough
Author{1}{Email}#=%=#brandcol@umd.edu
Author{1}{Affiliation}#=%=#NIH
Author{2}{Firstname}#=%=#Davis
Author{2}{Lastname}#=%=#Bartels
Author{2}{Username}#=%=#bartelsdp
Author{2}{Email}#=%=#davis.bartels@nih.gov
Author{2}{Affiliation}#=%=#National Institutes of Health
Author{3}{Firstname}#=%=#Dina
Author{3}{Lastname}#=%=#Demner-Fushman
Author{3}{Username}#=%=#dina
Author{3}{Email}#=%=#ddemner@gmail.com
Author{3}{Affiliation}#=%=#National Library of Medicine

==========
èéáğö