Multilingual Instruction Tuning With Just a Pinch of Multilinguality

Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor, Reut Tsarfaty, Matan Eyal


Abstract
As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a multilingual LLM affects instruction-following across languages from the pre-training corpus. We first show that many languages transfer some instruction-following capabilities to other languages from even monolingual tuning. Furthermore, we find that only 40 multilingual examples integrated in an English tuning set substantially improve multilingual instruction-following, both in seen and unseen languages during tuning. In general, we observe that models tuned on multilingual mixtures exhibit comparable or superior performance in multiple languages compared to monolingually tuned models, despite training on 10x fewer examples in those languages. Finally, we find that diversifying the instruction tuning set with even just 2-4 languages significantly improves cross-lingual generalization. Our results suggest that building massively multilingual instruction-tuned models can be done with only a very small set of multilingual instruction-responses.
Anthology ID:
2024.findings-acl.136
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2304–2317
Language:
URL:
https://aclanthology.org/2024.findings-acl.136
DOI:
10.18653/v1/2024.findings-acl.136
Bibkey:
Cite (ACL):
Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor, Reut Tsarfaty, and Matan Eyal. 2024. Multilingual Instruction Tuning With Just a Pinch of Multilinguality. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2304–2317, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Multilingual Instruction Tuning With Just a Pinch of Multilinguality (Shaham et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.136.pdf