Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910661032804352 |
|---|---|
| author | Chiaranaipanich, Jirat Hanmatheekuna, Naiyarat Sawatphol, Jitkapat Tiankanon, Krittamate Kinchagawat, Jiramet Chinkamol, Amrest Pengpun, Parinthapat Ittichaiwong, Piyalitt Limkonchotiwat, Peerat |
| author_facet | Chiaranaipanich, Jirat Hanmatheekuna, Naiyarat Sawatphol, Jitkapat Tiankanon, Krittamate Kinchagawat, Jiramet Chinkamol, Amrest Pengpun, Parinthapat Ittichaiwong, Piyalitt Limkonchotiwat, Peerat |
| contents | Large language models (LLMs) perform well on common tasks but struggle with generalization in low-resource and low-computation settings. We examine this limitation by testing various LLMs and specialized translation models on English-Thai machine translation and code-switching datasets. Our findings reveal that under more strict computational constraints, such as 4-bit quantization, LLMs fail to translate effectively. In contrast, specialized models, with comparable or lower computational requirements, consistently outperform LLMs. This underscores the importance of specialized models for maintaining performance under resource constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ? Chiaranaipanich, Jirat Hanmatheekuna, Naiyarat Sawatphol, Jitkapat Tiankanon, Krittamate Kinchagawat, Jiramet Chinkamol, Amrest Pengpun, Parinthapat Ittichaiwong, Piyalitt Limkonchotiwat, Peerat Computation and Language Artificial Intelligence Machine Learning Large language models (LLMs) perform well on common tasks but struggle with generalization in low-resource and low-computation settings. We examine this limitation by testing various LLMs and specialized translation models on English-Thai machine translation and code-switching datasets. Our findings reveal that under more strict computational constraints, such as 4-bit quantization, LLMs fail to translate effectively. In contrast, specialized models, with comparable or lower computational requirements, consistently outperform LLMs. This underscores the importance of specialized models for maintaining performance under resource constraints. |
| title | Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ? |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.17145 |