Pruning Multilingual Large Language Models for Multilingual Inference

Hwichan Kim, Jun Suzuki, Tosho Hirasawa, Mamoru Komachi


Abstract
Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. This study introduces a promising direction for enhancing non-English performance through a specialized pruning approach. Specifically, we prune MLLMs using bilingual sentence pairs from English and other languages and empirically demonstrate that this pruning strategy can enhance the MLLMs’ performance in non-English language.
Anthology ID:
2024.findings-emnlp.580
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9921–9942
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.580
DOI:
10.18653/v1/2024.findings-emnlp.580
Bibkey:
Cite (ACL):
Hwichan Kim, Jun Suzuki, Tosho Hirasawa, and Mamoru Komachi. 2024. Pruning Multilingual Large Language Models for Multilingual Inference. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9921–9942, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Pruning Multilingual Large Language Models for Multilingual Inference (Kim et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.580.pdf
Software:
 2024.findings-emnlp.580.software.zip
Data:
 2024.findings-emnlp.580.data.zip