DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning
Proceedings of the ACM on Management of Data · 02.04.2026 · 4 (1) · 1-24
DOI: 10.1145/3786640 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 07.04.2026. Verfasst von Yafeng Nan und 7 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, High-Quality Development Project of the MIIT, Ministry of Education and China Mobile Joint Fund.
Abstract (Originalsprache)
In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. State-of-the-art Text-to-SQL models have achieved impressive accuracy, but their performance critically relies on expert-written evidence. This evidence typically clarifies schema and value linking that existing models struggle to identify. Such limitations stem from the ambiguity of user queries and, more importantly, the complexity of comprehending large-scale and dynamic database values. Consequently, in real-world scenarios where expert assistance is unavailable, existing methods suffer a severe performance collapse, with execution accuracy dropping by over 10%. This underscores their lack of robustness due to the reliance on expert assistance. To address this, we propose DIVER, a robust system that automates evidence reasoning with dynamic interactive value linking. It leverages a compatible toolbox containing diverse tools to probe the database. Then, restricted by a structured workspace (CoTF, Chain of Thoughts and Facts) , it reflects based on probe results and selects a new tool for next round of probing. Through this automatically iterative process, DIVER identifies schema and value linking missed by existing methods. Based on these accurate linkings, DIVER is able to infer correct usage of SQL functions and formulas and generate high-quality evidence, achieving robust Text-to-SQL without expert assistance. Extensive experiments demonstrate that: 1) The DIVER system significantly enhances the robustness of various Text-to-SQL models, improving performance by up to 10.82% in Execution Accuracy (EX) and 16.09% in Valid Efficiency Score (VES). 2) Our dynamic interactive value linking significantly improves the robustness of existing systems and the accuracy of schema and value linking, especially when confronted with challenges posed by large-scale, dynamic database values.
Förderung
- National Natural Science Foundation of China
- High-Quality Development Project of the MIIT
- Ministry of Education and China Mobile Joint Fund
- China Postdoctoral Science Foundation
- Fundamental Research Funds for the Central Universities
- 2025 Education and Teaching Reform Project Funding at Beijing University of Posts and Telecommunications
Zitieren
APA
Nan, Y., Sun, H., Zhuang, Z., Qi, Q., Chu, G., Liao, J., Pei, D., & Wang, J. (2026). DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning. Proceedings of the ACM on Management of Data, 4(1), 1-24. https://doi.org/10.1145/3786640
Vancouver
Nan Y, Sun H, Zhuang Z, Qi Q, Chu G, Liao J, et al. DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning. Proceedings of the ACM on Management of Data. 2026;4(1):1-24. doi:10.1145/3786640
BibTeX
@article{Nan2026,
author = {Nan, Yafeng and Sun, Haifeng and Zhuang, Zirui and Qi, Qi and Chu, Guojun and Liao, Jianxin and Pei, Dan and Wang, Jingyu},
title = {DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning},
journal = {Proceedings of the ACM on Management of Data},
year = {2026},
volume = {4},
number = {1},
pages = {1--24},
doi = {10.1145/3786640}
}
EUVIMED