@inproceedings{grandury-etal-2025-la,
    title = "La Leaderboard: A Large Language Model Leaderboard for {S}panish Varieties and Languages of {S}pain and {L}atin {A}merica",
    author = "Grandury, Mar{\'i}a  and
      Aula-Blasco, Javier  and
      Falc{\~a}o, J{\'u}lia  and
      Fourrier, Cl{\'e}mentine  and
      Saiz, Miguel Gonz{\'a}lez  and
      Mart{\'i}nez, Gonzalo  and
      Gomez, Gonzalo Santamaria  and
      Agerri, Rodrigo  and
      Garc{\'i}a, Nuria Aldama  and
      Chiruzzo, Luis  and
      Conde, Javier  and
      Gomez Adorno, Helena  and
      Nieto, Marta Guerrero  and
      Ivetta, Guido  and
      Fuertes, Nat{\`a}lia L{\'o}pez  and
      Plaza-del-Arco, Flor Miriam  and
      Mart{\'i}n-Valdivia, Mar{\'i}a-Teresa  and
      Zamorano, Helena Montoro  and
      Sanz, Carmen Mu{\~n}oz  and
      Reviriego, Pedro  and
      Plaza, Leire Rosado  and
      Vaca Serrano, Alejandro  and
      Vallecillo-Rodr{\'i}guez, Estrella  and
      Vallego, Jorge  and
      Zubiaga, Irune",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1561/",
    pages = "32482--32524",
    ISBN = "979-8-89176-251-0",
    abstract = "Leaderboards showcase the current capabilities and limitations of Large Language Models (LLMs). To motivate the development of LLMs that represent the linguistic and cultural diversity of the Spanish-speaking community, we present La Leaderboard, the first open-source leaderboard to evaluate generative LLMs in languages and language varieties of Spain and Latin America. La Leaderboard is a community-driven project that aims to establish an evaluation standard for everyone interested in developing LLMs for the Spanish-speaking community. This initial version combines 66 datasets in Catalan, Basque, Galician, and different Spanish varieties, showcasing the evaluation results of 50 models. To encourage community-driven development of leaderboards in other languages, we explain our methodology, including guidance on selecting the most suitable evaluation setup for each downstream task. In particular, we provide a rationale for using fewer few-shot examples than typically found in the literature, aiming to reduce environmental impact and facilitate access to reproducible results for a broader research community."
}