Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li


Abstract
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: https://github.com/FlyingFeather/DEA-SQL.
Anthology ID:
2024.findings-acl.641
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10796–10816
Language:
URL:
https://aclanthology.org/2024.findings-acl.641
DOI:
10.18653/v1/2024.findings-acl.641
Bibkey:
Cite (ACL):
Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, and Zang Li. 2024. Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10796–10816, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (Xie et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.641.pdf