Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908371101155328 |
|---|---|
| author | Wu, Zhanglin Wei, Daimeng Chen, Xiaoyu Shang, Hengchao Guo, Jiaxin Li, Zongyao Luo, Yuanchang Yang, Jinlong Rao, Zhiqiang Yang, Hao |
| author_facet | Wu, Zhanglin Wei, Daimeng Chen, Xiaoyu Shang, Hengchao Guo, Jiaxin Li, Zongyao Luo, Yuanchang Yang, Jinlong Rao, Zhiqiang Yang, Hao |
| contents | Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our evaluation, in most cases, translations using LLMs are comparable to that generated by neural machine translation (NMT) systems. Only in particular scenarios, LLM and NMT models show respective advantages. As a result, integrating NMT and LLM for translation and using LLM only when necessary seems to be a sound solution. A scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible is thereby required. We compare several scheduling policies and propose a novel and straightforward decider that leverages source sentence features. We conduct extensive experiments on multilingual test sets and the result shows that we can achieve optimal translation performance with minimal LLM usage, demonstrating effectiveness of our decider. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_13554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Wu, Zhanglin Wei, Daimeng Chen, Xiaoyu Shang, Hengchao Guo, Jiaxin Li, Zongyao Luo, Yuanchang Yang, Jinlong Rao, Zhiqiang Yang, Hao Computation and Language Artificial Intelligence Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our evaluation, in most cases, translations using LLMs are comparable to that generated by neural machine translation (NMT) systems. Only in particular scenarios, LLM and NMT models show respective advantages. As a result, integrating NMT and LLM for translation and using LLM only when necessary seems to be a sound solution. A scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible is thereby required. We compare several scheduling policies and propose a novel and straightforward decider that leverages source sentence features. We conduct extensive experiments on multilingual test sets and the result shows that we can achieve optimal translation performance with minimal LLM usage, demonstrating effectiveness of our decider. |
| title | Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.13554 |