Finetuning LLMs for EvaCun 2025 token prediction shared task

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jon, Josef, Bojar, Ondřej
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908599522951168
author Jon, Josef
Bojar, Ondřej
author_facet Jon, Josef
Bojar, Ondřej
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15561
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finetuning LLMs for EvaCun 2025 token prediction shared task
Jon, Josef
Bojar, Ondřej
Computation and Language
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.
title Finetuning LLMs for EvaCun 2025 token prediction shared task
topic Computation and Language
url https://arxiv.org/abs/2510.15561