{
 "id": "Vicomtech/just-eval-instruct-eu",
 "owner": "Vicomtech",
 "name": "just-eval-instruct-eu",
 "downloads": 5,
 "likes": 0,
 "last_modified": "2026-05-11T12:15:09.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "```bibtex\n@inproceedings{ponce-etal-2026-judging,\n  title = {Judging Instruction Responses in a Low-Resource Language: A Case Study on Basque},\n  author = {Ponce, David and Gete, Harritxu and Etchegoyhen, Thierry and Zubiaga, Irune and Soroa, Aitor},\n  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},\n  month = {May},\n  year = {2026},\n  pages = {281--298},\n  address = {Palma, Mallorca, Spain},\n  publisher = {European Language Resources Association (ELRA)},\n  editor = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},\n  doi = {10.63317/32e7ij6myh5i},\n  abstract = {Evaluating the quality of answers to a given instruction is a demanding and time-consuming task, limiting the scalability of human assessment. Large language models (LLMs) have been proposed as automatic judges to reduce this effort, but their reliability in low-resource contexts remains uncertain. Additionally, the premise that humans are reliable judges of fine-grained response quality needs to be assessed as well, if correlation with automated judges on this task is to be considered a gold standard. In this work, we investigate the performance of various LLM-as-a-judge in a low-resource scenario, namely Basque, and evaluate its correlation with human judgements. Additionally, we measure the agreement between human judgments themselves, to assess their viability as a valid reference. To perform our experi",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "b651b97a92cd76a9ea23b0005da8f19f5304c5b8",
 "stated_evidence": "https://huggingface.co/datasets/Vicomtech/just-eval-instruct-eu/blob/b651b97a92cd76a9ea23b0005da8f19f5304c5b8/README.md",
 "file_evidence": "https://huggingface.co/datasets/Vicomtech/just-eval-instruct-eu/tree/b651b97a92cd76a9ea23b0005da8f19f5304c5b8",
 "card_nc": false
}