Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning)
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908683498160128 |
|---|---|
| author | Padovani, Francesca Bunzeck, Bastian Ali, Manar Momen, Omar Bisazza, Arianna Buschmeier, Hendrik Zarrieß, Sina |
| author_facet | Padovani, Francesca Bunzeck, Bastian Ali, Manar Momen, Omar Bisazza, Arianna Buschmeier, Hendrik Zarrieß, Sina |
| contents | We investigate whether pre-training exclusively on dialogue data results in formally and functionally apt small language models. Based on this pre-trained llamalogue model, we employ a variety of fine-tuning strategies to enforce "more communicative" text generations by our models. Although our models underperform on most standard BabyLM benchmarks, they excel at dialogue continuation prediction in a minimal pair setting. While PPO fine-tuning has mixed to adversarial effects on our models, DPO fine-tuning further improves their performance on our custom dialogue benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20358 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning) Padovani, Francesca Bunzeck, Bastian Ali, Manar Momen, Omar Bisazza, Arianna Buschmeier, Hendrik Zarrieß, Sina Computation and Language We investigate whether pre-training exclusively on dialogue data results in formally and functionally apt small language models. Based on this pre-trained llamalogue model, we employ a variety of fine-tuning strategies to enforce "more communicative" text generations by our models. Although our models underperform on most standard BabyLM benchmarks, they excel at dialogue continuation prediction in a minimal pair setting. While PPO fine-tuning has mixed to adversarial effects on our models, DPO fine-tuning further improves their performance on our custom dialogue benchmark. |
| title | Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning) |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.20358 |