1. Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpus
- Author
-
Joshi, Raviraj, Singla, Kanishk, Kamath, Anusha, Kalani, Raunak, Paul, Rakesh, Vaidya, Utkarsh, Chauhan, Sanjay Singh, Wartikar, Niranjan, and Long, Eileen
- Subjects
Computer Science - Computation and Language ,Computer Science - Machine Learning - Abstract
Multilingual LLMs support a variety of languages; however, their performance is suboptimal for low-resource languages. In this work, we emphasize the importance of continued pre-training of multilingual LLMs and the use of translation-based synthetic pre-training corpora for improving LLMs in low-resource languages. We conduct our study in the context of the low-resource Indic language Hindi. We introduce Nemotron-Mini-Hindi 4B, a bilingual SLM supporting both Hindi and English, based on Nemotron-Mini 4B. The model is trained using a mix of real and synthetic Hindi + English tokens, with continuous pre-training performed on 400B tokens. We demonstrate that both the base and instruct models achieve state-of-the-art results on Hindi benchmarks while remaining competitive on English tasks. Additionally, we observe that the continued pre-training approach enhances the model's overall factual accuracy.
- Published
- 2024