Dear Colleagues,
We are pleased to announce that the ClinIQLink 2025 CodaBench Testing Framework is now live and ready for model submissions:
CodaBench Competition Page: https://www.codabench.org/competitions/5117/
This is an important milestone in the shared task, allowing participants to test their models under real evaluation conditions ahead of the April 15, 2025 submission deadline. With almost 40 participants and growing, we encourage early engagement to refine methodologies and optimize performance.
Why Participate?
ClinIQLink 2025, part of the BioNLP Workshop at ACL 2025, evaluates models on their ability to retrieve accurate medical knowledge and analyze hallucinations in generative responses. This challenge provides an opportunity to benchmark systems, advance research in medical AI, and contribute to a deeper understanding of knowledge retrieval in generative models.
Getting Started with CodaBench
Participants should begin testing their models as soon as possible. Submission guidelines and instructions are available on the challenge page:
* CodaBench ClinIQLink Docker Setup (GitHub): https://github.com/Brandonio-c/ClinIQLink_CodaBench_docker-setup * Submission Guidelines: Models under 10GB can be submitted directly to CodaBench, while models between 10GB and 750GB must be uploaded via Globus following the instructions provided on the challenge homepage. * Globus Connect Personal (Required for Uploading Large Models): https://www.globus.org/globus-connect-personal
Key Upcoming Deadlines
* April 15, 2025 – System Submission Deadline * April 25, 2025 – Results Feedback Provided * May 15, 2025 – Final Paper Submission Deadline * July 31, 2025 – BioNLP Workshop at ACL 2025
Useful Links
* Official Challenge Page: https://brandonio-c.github.io/ClinIQLink-2025/ * Sample Dataset: https://github.com/Brandonio-c/ClinIQLink_Sample-dataset * Google Form for Large Model Submission (10GB - 750GB): https://docs.google.com/forms/d/e/1FAIpQLSerRZnVHm-Trk9eYp6ebrJHQKTPvSBrI6nB...
For any questions or further details, please feel free to reach out.
Contact: Brandon Colelough – brandon.colelough@nih.govmailto:brandon.colelough@nih.gov
We look forward to your participation and contributions to this initiative. Kind regards,
Brandon Colelough (He / Him)
[News, Events, and Updates]NIH Fellow | Fulbright Scholar | ADF Signals Officer | Electrical Engineer National Institutes of Health – National Library of Medicine (LHC) M: +61 481 269 667tel:+61481269667 (AUS) | M: +1 (202) 367-7230tel:+12023677230 (US) E: brandcol@umd.edumailto:brandcol@umd.edu | E: brandon.colelough@gmail.commailto:brandon.colelough@gmail.com L: www.linkedin.com/in/brandon-coleloughhttps://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.linkedin.com%2Fin%2Fbrandon-colelough-853296194&data=05%7C02%7Cbrandon.colelough%40nih.gov%7C72376e92177e433f45aa08dc9ac6d3b2%7C14b77578977342d58507251ca2dc2b06%7C0%7C0%7C638555425971995708%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=1I95BjjvXOCu5VFz6HyQNgbJV6RQZk9or4KY0ZjpKqw%3D&reserved=0