DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning

2026-02-12

AI Summary

Existing Text-to-SQL systems struggle with query ambiguity and large-scale dynamic database values in the absence of expert-annotated evidence, leading to insufficient robustness. This work proposes an automatic, human-intervention-free evidence reasoning framework that integrates dynamic interactive value linking with a structured “Chain-of-Thought-and-Fact” (CoTF) workspace. Through iterative rounds of database probing, self-reflection, and high-quality evidence generation, the approach significantly enhances model generalization and linking accuracy in real-world scenarios. Experimental results demonstrate substantial improvements, with up to a 10.82% gain in execution accuracy (EX) and a 16.09% increase in Valid Efficiency Score (VES).

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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 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.

Problem

• Text-to-SQL
• schema linking
• value linking
• robustness
• dynamic database values

Innovation

• Dynamic Interactive Value Linking
• Evidence Reasoning
• Robust Text-to-SQL
• Chain of Thoughts and Facts
• Automated Schema Linking