北京大学学报（自然科学版）2026，Vol.62Issue(2)：266-274,9.DOI:10.13209/j.0479-8023.2025.097
融合CINO-LoRA和Self-condition的DiffuSum藏文文本自动摘要
Automatic Summarization of Tibetan Texts Using DiffuSum with CINO-LoRA and Self-condition Integration
摘要
Abstract
To further improve the performance of Tibetan text automatic summarization,the paper proposes a Tibetan text summarization model TiDiffuSum,which integrates CINO-LoRA and Self-condition into the DiffuSum to address issues of insufficient sentence representation,large parameter scale limiting contextual modeling,and high training costs in the Tibetan task.TiDiffuSum model introduces CINO-LoRA mechanism into the sentence encoder to enhance Tibetan semantic representation and significantly reduce the number of training parameters.Additionally,it incorporates Self-condition strategy in the diffusion generation module to strengthen the comprehension and utilization of contextual semantics.Experimental results indicate that TiDiffuSum can effectively reduce the parameter count to 0.45%of the baseline model on the Tibetan summarization dataset(TSUM),and achieves improvements of 1.07,0.78,and 1.08 in ROUGE-1,ROUGE-2,and ROUGE-L scores,significantly outperforming baseline models.关键词
藏文/文本自动摘要/DiffuSum模型/句子表征Key words
Tibetan/text automatic summarization/Diffusum model/sentence representation引用本文复制引用
王蓉,才智杰..融合CINO-LoRA和Self-condition的DiffuSum藏文文本自动摘要[J].北京大学学报（自然科学版）,2026,62(2):266-274,9.基金项目
国家自然科学基金(616966031,6186646462)资助 （616966031,6186646462）
