Annif at the GermEval-2025 LLMs4Subjects Task: Traditional XMTC Augmented by Efficient LLMs
By: Osma Suominen, Juho Inkinen, Mona Lehtinen
Potential Business Impact:
Helps libraries find books faster using smart computers.
This paper presents the Annif system in the LLMs4Subjects shared task (Subtask 2) at GermEval-2025. The task required creating subject predictions for bibliographic records using large language models, with a special focus on computational efficiency. Our system, based on the Annif automated subject indexing toolkit, refines our previous system from the first LLMs4Subjects shared task, which produced excellent results. We further improved the system by using many small and efficient language models for translation and synthetic data generation and by using LLMs for ranking candidate subjects. Our system ranked 1st in the overall quantitative evaluation of and 1st in the qualitative evaluation of Subtask 2.
Similar Papers
Annif at SemEval-2025 Task 5: Traditional XMTC augmented by LLMs
Computation and Language
Helps libraries automatically sort books by topic.
SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog
Computation and Language
Helps libraries sort science papers automatically.
DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing
Computation and Language
Tags library books automatically for better searching.