Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913216527859712 |
|---|---|
| author | Chen, Pinzhen Ji, Shaoxiong Bogoychev, Nikolay Kutuzov, Andrey Haddow, Barry Heafield, Kenneth |
| author_facet | Chen, Pinzhen Ji, Shaoxiong Bogoychev, Nikolay Kutuzov, Andrey Haddow, Barry Heafield, Kenneth |
| contents | Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_08958 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca Chen, Pinzhen Ji, Shaoxiong Bogoychev, Nikolay Kutuzov, Andrey Haddow, Barry Heafield, Kenneth Computation and Language Artificial Intelligence Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning. |
| title | Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2309.08958 |