Banzhida: Advancing Large Language Models for Tibetan with Curated Data and Continual Pre-Training (2507.09205v1)

Abstract: LLMs have achieved remarkable progress across many languages. However, Tibetan, as a representative low-resource language, is particularly underrepresented in existing models due to the scarcity of high-quality training corpora. To address this gap, we curate the largest Tibetan pre-training corpus to date, aggregating data from diverse sources and applying a dedicated data cleaning and processing pipeline tailored for Tibetan. With the curated data, we continue pre/post-training a multilingual base model into Banzhida, a multilingual LLM that advances generative AI for Tibetan. To evaluate the Tibetan capabilities of the model, we create new high-quality Tibetan benchmarks, and complement them with existing public benchmarks. Experimental results demonstrate that Banzhida consistently and significantly outperforms both open-source models of similar scale and Tibetan-tailored models across a wide range of tasks.