RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs

John Dang, Arash Ahmadian, Kelly Marchisio, Julia Kreutzer, Ahmet Üstün, Sara Hooker


Abstract
Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on a small set of high-resource languages like English and Chinese. This captures a small fraction of the languages in the world, but also makes it unclear which aspects of current state-of-the-art research transfer to a multilingual setting. In this work, we perform an exhaustive study to achieve a new state of the art in aligning multilingual LLMs. We introduce a novel, scalable method for generating high-quality multilingual feedback data to balance data coverage. We establish the benefits of cross-lingual transfer and increased dataset size in preference training. Our preference-trained model achieves a 54.4% win-rate against Aya 23 8B, the current state-of-the-art multilingual LLM in its parameter class, and a 69.5% win-rate or higher against widely used models like Gemma, Mistral and Llama 3. As a result of our efforts, we expand the frontier of alignment techniques to 23 languages, covering approximately half of the world’s population.
Anthology ID:
2024.emnlp-main.729
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13134–13156
Language:
URL:
https://aclanthology.org/2024.emnlp-main.729
DOI:
Bibkey:
Cite (ACL):
John Dang, Arash Ahmadian, Kelly Marchisio, Julia Kreutzer, Ahmet Üstün, and Sara Hooker. 2024. RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13134–13156, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs (Dang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.729.pdf