作者位次 #15/17ACL 2026Poster· Natural Language Processing
From Curated Data to Scalable Models: Continual Pre-training of Dense and M o E Large Language Models for T ibetan
Lei Yang · Leiyu Pan · Bojian Xiong · Renren Jin · Shaowei Zhang · Yue Chen · Ling Shi · Jiang Zhou · Junru Wu · Zhen Wang · Jianxiang Peng · Juesi Xiao · Tianyu Dong · Zhuowen Han · Zhuo Chen · Yuqi Ren · Deyi Xiong
摘要
Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, yet their performance remains heavily biased toward high-resource languages. Tibetan, despite its cultural significance and large speaker population, is still substantially unde...