A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915037202874368 |
|---|---|
| author | Scalena, Daniel Fersini, Elisabetta Nissim, Malvina |
| author_facet | Scalena, Daniel Fersini, Elisabetta Nissim, Malvina |
| contents | Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. As an alternative to fine-tuning, we explore the potential of activation steering-based techniques to enhance model performance on Italian tasks. Through our experiments we show that Italian steering (i) can be successfully applied to different models, (ii) achieves performances comparable to, or even better than, fine-tuned models for Italian, and (iii) yields higher quality and consistency in Italian generations. We also discuss the utility of steering and fine-tuning in the contemporary LLM landscape where models are anyway getting high Italian performances even if not explicitly trained in this language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering Scalena, Daniel Fersini, Elisabetta Nissim, Malvina Computation and Language Machine Learning Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. As an alternative to fine-tuning, we explore the potential of activation steering-based techniques to enhance model performance on Italian tasks. Through our experiments we show that Italian steering (i) can be successfully applied to different models, (ii) achieves performances comparable to, or even better than, fine-tuned models for Italian, and (iii) yields higher quality and consistency in Italian generations. We also discuss the utility of steering and fine-tuning in the contemporary LLM landscape where models are anyway getting high Italian performances even if not explicitly trained in this language. |
| title | A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2411.18247 |