From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915767215194112 |
|---|---|
| author | Cui, Chaoqun Wang, Shijing Huang, Liangbin Gu, Qingqing Huang, Zhaolong Zeng, Xiao Mao, Wenji |
| author_facet | Cui, Chaoqun Wang, Shijing Huang, Liangbin Gu, Qingqing Huang, Zhaolong Zeng, Xiao Mao, Wenji |
| contents | The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01068 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization Cui, Chaoqun Wang, Shijing Huang, Liangbin Gu, Qingqing Huang, Zhaolong Zeng, Xiao Mao, Wenji Computation and Language Artificial Intelligence The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality. |
| title | From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.01068 |