English

MaLA-500: Massive Language Adaptation of Large Language Models

Computation and Language 2024-04-04 v2

Abstract

Large language models (LLMs) have advanced the state of the art in natural language processing. However, their predominant design for English or a limited set of languages creates a substantial gap in their effectiveness for low-resource languages. To bridge this gap, we introduce MaLA-500, a novel large language model designed to cover an extensive range of 534 languages. To train MaLA-500, we employ vocabulary extension and continued pretraining on LLaMA 2 with Glot500-c. Our intrinsic evaluation demonstrates that MaLA-500 is better at predicting the given texts of low-resource languages than existing multilingual LLMs. Moreover, the extrinsic evaluation of in-context learning shows that MaLA-500 outperforms previous LLMs on SIB200 and Taxi1500 by a significant margin, i.e., 11.68% and 4.82% marco-average accuracy across languages. We release MaLA-500 at https://huggingface.co/MaLA-LM

Keywords

Cite

@article{arxiv.2401.13303,
  title  = {MaLA-500: Massive Language Adaptation of Large Language Models},
  author = {Peiqin Lin and Shaoxiong Ji and Jörg Tiedemann and André F. T. Martins and Hinrich Schütze},
  journal= {arXiv preprint arXiv:2401.13303},
  year   = {2024}
}
R2 v1 2026-06-28T14:25:35.818Z