Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
This reduces costs for users of text-to-SQL systems, though it is incremental as it builds on existing schema representation ideas.
The paper tackled the high cost of state-of-the-art text-to-SQL methods by introducing 'N-rep' consistency, which achieves similar BIRD benchmark scores at only $0.039 per query compared to up to $0.46 per query for existing approaches.
LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM techniques including Chain-of-Thought (CoT), self-consistency, and fine-tuning. These methods can be costly at inference time, sometimes requiring over a hundred LLM calls with reasoning, incurring average costs of up to \$0.46 per query, while fine-tuning models can cost thousands of dollars. We introduce "N-rep" consistency, a more cost-efficient text-to-SQL approach that achieves similar BIRD benchmark scores as other more expensive methods, at only \$0.039 per query. N-rep leverages multiple representations of the same schema input to mitigate weaknesses in any single representation, making the solution more robust and allowing the use of smaller and cheaper models without any reasoning or fine-tuning. To our knowledge, N-rep is the best-performing text-to-SQL approach in its cost range.