Overview of GutBrainIE@CLEF 2025: Gut-Brain Interplay Information Extraction

Recent studies link the gut microbiota to mental health conditions and to neurodegenerative diseases such as Parkinson’s and Alzheimer’s. However, the rapid speed at which this research field is evolving presents a significant challenge for clinicians and researchers who have to keep pace with an ever-expanding volume of biomedical literature. In this context, automatic tools for extracting and structuring information from scientific texts are becoming essential to support the understanding of the gut-brain axis. GutBrainIE promotes the development of Natural Language Processing (NLP) systems capable of extracting structured specialized knowledge from biomedical texts related to the gut-brain axis, aiming to accelerate biomedical discoveries through automated Information Extraction (IE). GutBrainIE is part of the BioASQ Lab at CLEF 2025 and is organized within the context of the research project HEREDITARY, funded by the European Commission. The task includes four subtasks of increasing complexity, one dealing with Named Entity Recognition (NER) and the other three with Relation Extraction (RE), and comprises a dataset manually annotated for entities and relations structured into four quality tiers. This extended overview describes the subtasks, dataset, evaluation methodology, results, and participant approaches for the GutBrainIE-2025 task.