DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning
Yafeng Nan, Haifeng Sun, Zirui Zhuang, Qi Qi, Guojun Chu, Jianxin Liao, Dan Pei, Jingyu Wang

TL;DR
DIVER is a robust Text-to-SQL system that automates evidence reasoning and dynamic value linking, significantly improving accuracy and robustness in database query tasks without requiring expert input.
Contribution
It introduces a novel automated evidence reasoning approach with dynamic interactive value linking, enhancing robustness and accuracy of Text-to-SQL models in complex, real-world scenarios.
Findings
Performance improved by up to 10.82% in execution accuracy
Enhanced robustness in schema and value linking
Significant gains in handling large-scale, dynamic database values
Abstract
In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. The sota Text-to-SQL models have achieved impressive accuracy, but their performance critically relies on expert-written evidence, which 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. To address this, we propose DIVER, a robust system that automates evidence reasoning with dynamic interactive value linking. It leverages a compatible toolbox…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Database Systems and Queries · Natural Language Processing Techniques · Topic Modeling
