TY - GEN
T1 - DAC
T2 - 30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
AU - Wang, Dingzirui
AU - Dou, Longxu
AU - Zhang, Xuanliang
AU - Zhu, Qingfu
AU - Che, Wanxiang
N1 - Publisher Copyright:
©2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - Text-to-SQL is an important task that helps access databases by generating SQL queries. Currently, correcting the generated SQL based on large language models (LLMs) automatically is an effective method to enhance the quality of the generated SQL. However, previous research shows that it is hard for LLMs to detect mistakes in SQL directly, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that detecting and fixing mistakes based on the decomposed sub-tasks is easier than using SQL directly. Then, we introduce Decomposed Automation Correction (DAC), which first generates the entities and skeleton corresponding to the question, and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that, compared with the previous automation correction method, DAC improves performance by 1.4%
AB - Text-to-SQL is an important task that helps access databases by generating SQL queries. Currently, correcting the generated SQL based on large language models (LLMs) automatically is an effective method to enhance the quality of the generated SQL. However, previous research shows that it is hard for LLMs to detect mistakes in SQL directly, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that detecting and fixing mistakes based on the decomposed sub-tasks is easier than using SQL directly. Then, we introduce Decomposed Automation Correction (DAC), which first generates the entities and skeleton corresponding to the question, and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that, compared with the previous automation correction method, DAC improves performance by 1.4%
UR - https://www.scopus.com/pages/publications/105028969868
U2 - 10.18653/v1/2025.findings-emnlp.22
DO - 10.18653/v1/2025.findings-emnlp.22
M3 - 会议稿件
AN - SCOPUS:105028969868
T3 - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
SP - 385
EP - 402
BT - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
A2 - Christodoulopoulos, Christos
A2 - Chakraborty, Tanmoy
A2 - Rose, Carolyn
A2 - Peng, Violet
PB - Association for Computational Linguistics (ACL)
Y2 - 4 November 2025 through 9 November 2025
ER -