SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog
This addresses the problem of efficient catalog classification for digital libraries, but it is incremental as it applies existing LLM methods to a new task and dataset.
The paper tackled automated subject tagging for scientific and technical records using LLMs, with results showing effectiveness through quantitative metrics like precision, recall, and F1-score, and qualitative assessments by specialists.
We present SemEval-2025 Task 5: LLMs4Subjects, a shared task on automated subject tagging for scientific and technical records in English and German using the GND taxonomy. Participants developed LLM-based systems to recommend top-k subjects, evaluated through quantitative metrics (precision, recall, F1-score) and qualitative assessments by subject specialists. Results highlight the effectiveness of LLM ensembles, synthetic data generation, and multilingual processing, offering insights into applying LLMs for digital library classification.