Explaining novel senses using definition generation with open language models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fedorova, Mariia, Kutuzov, Andrey, Periti, Francesco, Scherrer, Yves
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918152175091712
author Fedorova, Mariia
Kutuzov, Andrey
Periti, Francesco
Scherrer, Yves
author_facet Fedorova, Mariia
Kutuzov, Andrey
Periti, Francesco
Scherrer, Yves
contents We apply definition generators based on open-weights large language models to the task of creating explanations of novel senses, taking target word usages as an input. To this end, we employ the datasets from the AXOLOTL'24 shared task on explainable semantic change modeling, which features Finnish, Russian and German languages. We fine-tune and provide publicly the open-source models performing higher than the best submissions of the aforementioned shared task, which employed closed proprietary LLMs. In addition, we find that encoder-decoder definition generators perform on par with their decoder-only counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26181
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explaining novel senses using definition generation with open language models
Fedorova, Mariia
Kutuzov, Andrey
Periti, Francesco
Scherrer, Yves
Computation and Language
We apply definition generators based on open-weights large language models to the task of creating explanations of novel senses, taking target word usages as an input. To this end, we employ the datasets from the AXOLOTL'24 shared task on explainable semantic change modeling, which features Finnish, Russian and German languages. We fine-tune and provide publicly the open-source models performing higher than the best submissions of the aforementioned shared task, which employed closed proprietary LLMs. In addition, we find that encoder-decoder definition generators perform on par with their decoder-only counterparts.
title Explaining novel senses using definition generation with open language models
topic Computation and Language
url https://arxiv.org/abs/2509.26181