Explaining novel senses using definition generation with open language models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| 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 |