Overview of BioASQ 2025: The Thirteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering

2025-08-28

AI Summary

The BioASQ 2025 Challenge addresses biomedical semantic indexing and question answering through six tasks: multilingual clinical summarization (MultiClinSum), Russian–English bilingual nested named entity linking (BioNNE-L), cardiology clinical coding (ELCardioCC), and gut–brain interaction information extraction (GutBrainIE), among others. Methodologically, participating systems integrate multilingual large language models, end-to-end generative architectures, nested named entity recognition, and fine-grained semantic linking techniques. The challenge introduces three novel paradigms: (i) multilingual clinical summarization, (ii) cross-lingual nested entity linking, and (iii) organ-system-specific information extraction—thereby expanding the frontiers of biomedical AI. Eighty-three teams submitted over 1,000 runs; top-performing systems demonstrated substantial improvements in clinical text understanding, abstractive generation, and structured information extraction, advancing state-of-the-art capabilities in biomedical natural language processing.

Technology Category

• Natural Language Processing: Summarization
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Medical and Biological Imaging

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

This is an overview of the thirteenth edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2025. BioASQ is a series of international challenges promoting advances in large-scale biomedical semantic indexing and question answering. This year, BioASQ consisted of new editions of the two established tasks, b and Synergy, and four new tasks: a) Task MultiClinSum on multilingual clinical summarization. b) Task BioNNE-L on nested named entity linking in Russian and English. c) Task ELCardioCC on clinical coding in cardiology. d) Task GutBrainIE on gut-brain interplay information extraction. In this edition of BioASQ, 83 competing teams participated with more than 1000 distinct submissions in total for the six different shared tasks of the challenge. Similar to previous editions, several participating systems achieved competitive performance, indicating the continuous advancement of the state-of-the-art in the field.

Problem

• Advancing biomedical semantic indexing through large-scale international challenges
• Improving multilingual question answering in clinical and biomedical domains
• Developing information extraction systems for specialized medical contexts

Innovation

• Multilingual clinical summarization task
• Nested named entity linking system
• Clinical coding in cardiology task