Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908344292212736 |
|---|---|
| author | Yakhni, Silvana Chehab, Ali |
| author_facet | Yakhni, Silvana Chehab, Ali |
| contents | This paper examines the effectiveness of Large Language Models (LLMs) in translating the low-resource Lebanese dialect, focusing on the impact of culturally authentic data versus larger translated datasets. We compare three fine-tuning approaches: Basic, contrastive, and grammar-hint tuning, using open-source Aya23 models. Experiments reveal that models fine-tuned on a smaller but culturally aware Lebanese dataset (LW) consistently outperform those trained on larger, non-native data. The best results were achieved through contrastive fine-tuning paired with contrastive prompting, which indicates the benefits of exposing translation models to bad examples. In addition, to ensure authentic evaluation, we introduce LebEval, a new benchmark derived from native Lebanese content, and compare it to the existing FLoRes benchmark. Our findings challenge the "More Data is Better" paradigm and emphasize the crucial role of cultural authenticity in dialectal translation. We made our datasets and code available on Github. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00114 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese Yakhni, Silvana Chehab, Ali Computation and Language Artificial Intelligence This paper examines the effectiveness of Large Language Models (LLMs) in translating the low-resource Lebanese dialect, focusing on the impact of culturally authentic data versus larger translated datasets. We compare three fine-tuning approaches: Basic, contrastive, and grammar-hint tuning, using open-source Aya23 models. Experiments reveal that models fine-tuned on a smaller but culturally aware Lebanese dataset (LW) consistently outperform those trained on larger, non-native data. The best results were achieved through contrastive fine-tuning paired with contrastive prompting, which indicates the benefits of exposing translation models to bad examples. In addition, to ensure authentic evaluation, we introduce LebEval, a new benchmark derived from native Lebanese content, and compare it to the existing FLoRes benchmark. Our findings challenge the "More Data is Better" paradigm and emphasize the crucial role of cultural authenticity in dialectal translation. We made our datasets and code available on Github. |
| title | Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00114 |