{"ID":2854064,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15561","arxiv_id":"2510.15561","title":"Finetuning LLMs for EvaCun 2025 token prediction shared task","abstract":"In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simply used the training data without any task-specific adjustments, preprocessing, or filtering. We compare 3 different approaches (based on 3 different prompts) of obtaining the predictions, and we evaluate them on a held-out part of the data.","short_abstract":"In this paper, we present our submission for the token prediction task of EvaCun 2025. Our sys-tems are based on LLMs (Command-R, Mistral, and Aya Expanse) fine-tuned on the task data provided by the organizers. As we only pos-sess a very superficial knowledge of the subject field and the languages of the task, we simp...","url_abs":"https://arxiv.org/abs/2510.15561","url_pdf":"https://arxiv.org/pdf/2510.15561v1","authors":"[\"Josef Jon\",\"Ondřej Bojar\"]","published":"2025-10-17T11:47:02Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}