C3: Zero-shot Text-to-SQL with ChatGPT
This addresses the challenge of generating SQL queries from natural language without task-specific training, which is incremental as it builds on existing large language models.
The paper tackles the problem of zero-shot Text-to-SQL conversion by proposing C3, a method based on ChatGPT, achieving 82.3% execution accuracy on the Spider dataset and setting a new state-of-the-art for zero-shot approaches.
This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82.3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge. C3 consists of three key components: Clear Prompting (CP), Calibration with Hints (CH), and Consistent Output (CO), which are corresponding to the model input, model bias and model output respectively. It provides a systematic treatment for zero-shot Text-to-SQL. Extensive experiments have been conducted to verify the effectiveness and efficiency of our proposed method.