Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
This addresses performance issues in text-to-SQL for database query applications, but it is incremental as it builds on existing LLM and prompting methods.
The paper tackled the problem of attention diffusion and inadequate performance in LLM-based text-to-SQL tasks by proposing a workflow paradigm method with decomposition, achieving about 2-3 percentage point improvements on multiple datasets and new SOTA results on Spider Test.
In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition. Specifically, the information determination module for eliminating redundant information and the brand-new prompt structure based on problem classification greatly enhance the model's attention. Additionally, the inclusion of self-correction and active learning modules greatly expands the problem-solving scope of LLMs, hence improving the upper limit of LLM-based approaches. Extensive experiments conducted on three datasets demonstrate that our approach outperforms other methods by a significant margin. About 2-3 percentage point improvements compared to the existing baseline on the Spider Dev, Spider-Realistic, and Bird Dev datasets and new SOTA results on the Spider Test dataset are achieved. Our code is available on GitHub: \url{https://github.com/FlyingFeather/DEA-SQL}.