Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.10336 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911312941940736 |
|---|---|
| author | Lahmi, Jules Roger, Alexis |
| author_facet | Lahmi, Jules Roger, Alexis |
| contents | Artificial intelligence has made great progress in recent years, particularly in the development of Vision--Language Models (VLMs) that understand both visual and textual data. However, these advancements remain largely limited to English, reducing their accessibility for non--English speakers. It is essential to extend these capabilities to a broader range of languages. This paper explores the challenges of adapting an English-trained VLM to different languages. To this end, we will explore and compare different methods for their performance and computational cost. We consider a translation-based pipeline, LoRA finetuning, and a two-stage finetuning strategy that separates vision adaptation from language adaptation. To evaluate these methods, we use a combination of standard multimodal benchmarks translated into the target language and manual assessments by native experts. The results reveal that dataset translation remains a major bottleneck in multilingual VLM performance, with data quality limiting the effectiveness of training and evaluation. These findings suggest that future efforts should focus on native-language dataset collection and improved translation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multilingual VLM Training: Adapting an English-Trained VLM to French Lahmi, Jules Roger, Alexis Computation and Language Artificial Intelligence Artificial intelligence has made great progress in recent years, particularly in the development of Vision--Language Models (VLMs) that understand both visual and textual data. However, these advancements remain largely limited to English, reducing their accessibility for non--English speakers. It is essential to extend these capabilities to a broader range of languages. This paper explores the challenges of adapting an English-trained VLM to different languages. To this end, we will explore and compare different methods for their performance and computational cost. We consider a translation-based pipeline, LoRA finetuning, and a two-stage finetuning strategy that separates vision adaptation from language adaptation. To evaluate these methods, we use a combination of standard multimodal benchmarks translated into the target language and manual assessments by native experts. The results reveal that dataset translation remains a major bottleneck in multilingual VLM performance, with data quality limiting the effectiveness of training and evaluation. These findings suggest that future efforts should focus on native-language dataset collection and improved translation strategies. |
| title | Multilingual VLM Training: Adapting an English-Trained VLM to French |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.10336 |