Annif at the GermEval-2025 LLMs4Subjects Task: Traditional XMTC Augmented by Efficient LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916911878504448 |
|---|---|
| author | Suominen, Osma Inkinen, Juho Lehtinen, Mona |
| author_facet | Suominen, Osma Inkinen, Juho Lehtinen, Mona |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15877 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Annif at the GermEval-2025 LLMs4Subjects Task: Traditional XMTC Augmented by Efficient LLMs Suominen, Osma Inkinen, Juho Lehtinen, Mona Computation and Language Artificial Intelligence Information Retrieval Machine Learning I.2.7 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. |
| title | Annif at the GermEval-2025 LLMs4Subjects Task: Traditional XMTC Augmented by Efficient LLMs |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning I.2.7 |
| url | https://arxiv.org/abs/2508.15877 |