PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913547390287872 |
|---|---|
| author | Sun, Shuqiao Yao, Yutong Wu, Peiwen Jiang, Feijun Zhang, Kaifu |
| author_facet | Sun, Shuqiao Yao, Yutong Wu, Peiwen Jiang, Feijun Zhang, Kaifu |
| contents | Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles. In this paper, a new method is proposed to effectively generate large-scale multilingual parallel corpora with specific translation preferences using Large Language Models (LLMs). Meanwhile, an automatic pipeline is designed to distill human preferences into smaller Machine Translation (MT) models for efficiently and economically supporting large-scale calls in online services. Experiments indicate that the proposed method takes the lead in translation tasks with aligned human preferences by a large margin. Meanwhile, on popular public benchmarks like WMT and Flores, on which our models were not trained, the proposed method also shows a competitive performance compared to SOTA works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11410 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation Sun, Shuqiao Yao, Yutong Wu, Peiwen Jiang, Feijun Zhang, Kaifu Computation and Language Artificial Intelligence Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles. In this paper, a new method is proposed to effectively generate large-scale multilingual parallel corpora with specific translation preferences using Large Language Models (LLMs). Meanwhile, an automatic pipeline is designed to distill human preferences into smaller Machine Translation (MT) models for efficiently and economically supporting large-scale calls in online services. Experiments indicate that the proposed method takes the lead in translation tasks with aligned human preferences by a large margin. Meanwhile, on popular public benchmarks like WMT and Flores, on which our models were not trained, the proposed method also shows a competitive performance compared to SOTA works. |
| title | PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.11410 |