Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages
Zeli Su, Ziyin Zhang, Guixian Xu, Jianing Liu, Xu Han, Ting Zhang, Yushuang Dong
Abstract
While multilingual language models like XLM-R have advanced multilingualism in NLP, they still perform poorly in extremely low-resource languages. This situation is exacerbated by the fact that modern LLMs such as LLaMA and Qwen support far fewer languages than XLM-R, making text generation models non-existent for many languages in the world. To tackle this challenge, we propose a novel framework for adapting multilingual encoders to text generation in extremely low-resource languages. By reusing the weights between the encoder and the decoder, our framework allows the model to leverage the learned semantic space of the encoder, enabling efficient learning and effective generalization in low-resource languages. Applying this framework to four Chinese minority languages, we present XLM-SWCM, and demonstrate its superior performance on various downstream tasks even when compared with much larger models.
BibTeX
@inproceedings{su-etal-2025-multilingual,
title = "Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages",
author = "Su, Zeli and
Zhang, Ziyin and
Xu, Guixian and
Liu, Jianing and
Han, Xu and
Zhang, Ting and
Dong, Yushuang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.893/",
doi = "10.18653/v1/2025.acl-long.893",
pages = "18259--18270",
ISBN = "979-8-89176-251-0"
}