Guy Bilitski, Lev Shechter, Sonam Jamtsho, Nir Marciano, Nicola Bajetta, Rebecca Sunden, Omri Drori, Kai Golan Hashiloni, Orr Zwebner, Asaf Shina, Orna Almogi, Dorji Wangchuk, Kfir Bar, 2026.
We introduce a new computational framework for segmenting Classical Tibetan texts into autochthonous and allochthonous regions, distinguishing between indigenous Tibetan compositions and translated materials, primarily from Sanskrit sources. To support this task, we release the first annotated Tibetan corpus for autochthonous–allochthonous segmentation and evaluate several multilingual encoders, including mBERT, XLM-R and our own pre-trained model, fine-tuned for sequence labeling. Our model had the best performance, achieving strong alignment with expert annotations, showing that multilingual representations can effectively capture philological boundaries in low-resource settings. This work contributes new resources and methods for computational philology and sheds light on linguistic markers that trace the intercultural evolution and transmission of Buddhist texts in Tibet.