Rationalization Models for Text-to-SQL

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.

@article{rossiello2025_2502.06759,
  title={ Rationalization Models for Text-to-SQL },
  author={ Gaetano Rossiello and Nhan Pham and Michael Glass and Junkyu Lee and Dharmashankar Subramanian },
  journal={arXiv preprint arXiv:2502.06759},
  year={ 2025 }
}