Rationalization Models for Text-to-SQL
This work addresses the challenge of generating accurate and explainable SQL queries from natural language, which is incremental as it builds on existing text-to-SQL methods by incorporating rationales.
The paper tackles the problem of improving text-to-SQL models by generating Chain-of-Thought rationales with intermediate SQL statements and explanations, and results show that this approach enhances execution accuracy, particularly for complex queries, on the BIRD dataset.
We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing the final SQL query. The process begins with manually annotating a small set of examples, which are then used to prompt a large language model in an iterative, dynamic few-shot knowledge distillation procedure from a teacher model. A rationalization model is subsequently trained on the validated decomposed queries, enabling extensive synthetic CoT annotations for text-to-SQL datasets. To evaluate the approach, we fine-tune small language models with and without these rationales on the BIRD dataset. Results indicate that step-by-step query generation improves execution accuracy, especially for moderately and highly complex queries, while also enhancing explainability.