HIT-SCIR at CCKS-IJCKG2024: Enhancing Text-to-SQL with Multi-step Pipeline

HIT-SCIR at CCKS-IJCKG2024: Enhancing Text-to-SQL with Multi-step Pipeline

연구 분야: Databases

학회: China Conference on Knowledge Graph and Semantic Computing

The text-to-SQL task translates natural language questions into SQL queries, simplifying database access. While large language models (LLMs) have shown strong performance, they often struggle with complex reasoning, such as commonsense and numerical reasoning, required for more challenging SQL generation. We propose a new pipeline that enhances SQL generation by incorporating advanced reasoning skills, alongside techniques like entity linking and self-correction. Tested on the Archer dataset, which requires more complex reasoning, our approach improves performance by over the baseline, demonstrating its effectiveness in handling challenging queries.