On-the-Fly Fusion of Large Language Models and Machine Translation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911867388035072 |
|---|---|
| author | Hoang, Hieu Khayrallah, Huda Junczys-Dowmunt, Marcin |
| author_facet | Hoang, Hieu Khayrallah, Huda Junczys-Dowmunt, Marcin |
| contents | We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models. We combine our method with various techniques from LLM prompting, such as in context learning and translation context. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_08306 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | On-the-Fly Fusion of Large Language Models and Machine Translation Hoang, Hieu Khayrallah, Huda Junczys-Dowmunt, Marcin Computation and Language We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models. We combine our method with various techniques from LLM prompting, such as in context learning and translation context. |
| title | On-the-Fly Fusion of Large Language Models and Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.08306 |