Earlier this year, the Annif team participated in the LLMs4Subjects challenge, where our automated indexing tool performed nicely! 🏆 We also got new ideas for Annif development out of the challenge! The SemEval-2025 workshop proceedings are now available 👉 https://aclanthology.org/volumes/2025.semeval-1/
The work continued with the GermEval workshop, focusing on resource efficiency, and we did very well!🥇Check out our GermEval pre-print 👉 https://doi.org/10.48550/arXiv.2508.15877 🤖
#LLMs4Subjects #Annif #SemEval2025 #AI #SubjectIndexing
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) - ACL Anthology

Annif-tiimi osallistui alkuvuodesta LLMs4Subjects-haasteeseen, jossa automaattisen asiasanoituksen työkalumme pärjäsi hienosti! 🏆 Saimme kisasta uusia ideoita Annifin kehitykseen! SemEval-2025-työpajan julkaisut ovat nyt luettavissa 👉 https://aclanthology.org/volumes/2025.semeval-1/
Haaste jatkui GermEval-työpajan muodossa, jossa keskityttiin mallien resurssitehokkuuteen, ja sijoituimme taas mainiosti!🥇Lue esijulkaisumme GermEval-kisasta 👉 https://doi.org/10.48550/arXiv.2508.15877 🤖
#LLMs4Subjects #Annif #SemEval2025 #AI #Asiasanoitus
Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) - ACL Anthology

We are also participating in the 2nd #LLMs4Subjects challenge at the GermEval-2025 workshop. Expect to see an even better automated subject indexing system based on combining #Annif and #LLMs!

https://sites.google.com/view/llms4subjects-germeval/home

The theme for the 2nd installment is "energy- and compute-efficient LLMs", so we will focus on building solutions based on smaller, more efficient, local AI models rather than huge, general purpose cloud LLMs.

Home

Our Mission We believe libraries are at the heart of our society and education, therefore we believe in impacting technological innovation in these age-old institutions as well as modern digital libraries when we can! We believe in transforming workflows in modern digital library systems... We

In the first #LLMs4Subjects challenge at the SemEval-2025 workshop, our #Annif team did very well!

The challenge was to generate good quality subject indexing for bibliographic records in German & English using LLMs. We used LLMs for data preprocessing (translation & synthetic data) and Annif as the main suggestion engine. We ranked 1st and 2nd in quantitative and 4th in qualitative evaluations out of 14 teams!

More info & preprints: https://groups.google.com/g/annif-users/c/b8kVy6XSzB4/m/JE6xBzSuEgAJ

#subjectIndexing #AI #LLM #SemEval

Annif awarded at the LLMs4Subjects challenge