COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning

Jaeseong Lee, YeonJoon Jung, Seung-won Hwang


Abstract
Recently, instruction-tuned large language models (LLMs) are showing prominent performance on various tasks, such as question answering. However, the majority of instruction-tuned LLMs are English-centric, which hinders their application to low-resource language QA. In this paper, we propose COde-Mixed Multilingual Instruction Tuning (COMMIT) to adapt English-centric LLM to low-resource language QA. We point out two main causes of English-centricness: imbalance of unlabeled data, and English-centric instruction tuning datasets. To deviate from English-centric instruction tuning, we propose to specialize code-mixing for instruction tuning, which blocks code-mixing in English templates, to leverage the potential of its superiority. To overcome data imbalance, we perform cross-lingual alignment. The majority of cross-lingual alignment works focused on making representations similar, which is not desirable to decoder-based LLMs, such as LLaMA. Therefore, we propose code-mixed continual causal language modeling to align the decoder. COMMIT improves the exact match score of low-resourced language QA by up to 32x. Code is publicly available.
Anthology ID:
2024.findings-naacl.198
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3130–3137
Language:
URL:
https://aclanthology.org/2024.findings-naacl.198
DOI:
Bibkey:
Cite (ACL):
Jaeseong Lee, YeonJoon Jung, and Seung-won Hwang. 2024. COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3130–3137, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning (Lee et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.198.pdf
Copyright:
 2024.findings-naacl.198.copyright.pdf