Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.09454 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915478240231424 |
|---|---|
| author | Marmonier, Malik Bawden, Rachel Sagot, Benoît |
| author_facet | Marmonier, Malik Bawden, Rachel Sagot, Benoît |
| contents | This study explores an LLM's ability to learn new languages using explanations found in a grammar book, a process we term "explicit learning." To rigorously assess this ability, we design controlled translation experiments between English and constructed languages generated, through specific cryptographic means, from Latin or French. Contrary to previous studies, our results demonstrate that LLMs do possess a measurable capacity for explicit learning. This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases. Supervised fine-tuning on ad hoc chains of thought significantly enhances LLM performance but struggles to generalize to typologically novel or more complex linguistic features. These findings point to the need for more diverse training sets and alternative fine-tuning strategies to further improve explicit learning by LLMs, benefiting low-resource languages typically described in grammar books but lacking extensive corpora. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09454 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explicit Learning and the LLM in Machine Translation Marmonier, Malik Bawden, Rachel Sagot, Benoît Computation and Language This study explores an LLM's ability to learn new languages using explanations found in a grammar book, a process we term "explicit learning." To rigorously assess this ability, we design controlled translation experiments between English and constructed languages generated, through specific cryptographic means, from Latin or French. Contrary to previous studies, our results demonstrate that LLMs do possess a measurable capacity for explicit learning. This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases. Supervised fine-tuning on ad hoc chains of thought significantly enhances LLM performance but struggles to generalize to typologically novel or more complex linguistic features. These findings point to the need for more diverse training sets and alternative fine-tuning strategies to further improve explicit learning by LLMs, benefiting low-resource languages typically described in grammar books but lacking extensive corpora. |
| title | Explicit Learning and the LLM in Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.09454 |