Database Tibetan Query Optimization Based on Generated TSpider Dataset and Input Feature Enhanced Large Language Models
摘要
Relational database querying in Tibetan remains a markedly low-resourced endeavor. Existing Text-to-SQL models have only been evaluated on English or Chinese corpora, leaving Tibetan entirely unexplored. To address these issues, TSpider as the first Tibetan Text-to-SQL dataset is constructed by translating the CSpider corpus and comprising 11,840 Tibetan natural-language queries. Furthermore, the Input Feature Enhancement (IFE)-LLM framework is employed: its cross-encoder is adapted to Tibetan by integrating CINO, and the downstream open-source large language model is then prompted to generate executable SQLite SQL statements. Experimental evaluation on TSpider reveals that our framework attains 31.8% exact-match and 62.1% execution accuracy, establishing the first baseline for Tibetan Text-to-SQL and validating its efficacy in generating SQL from low-resource Tibetan text.