MCI-SQL: Text-to-SQL with Metadata-Complete Context and Intermediate Correction

2026-03-11

AI Summary

This work addresses the limitations of existing Text-to-SQL approaches, which suffer from inaccurate column filtering during schema linking and are prone to reasoning errors that degrade overall performance. To mitigate these issues, we propose three key techniques: a metadata-enriched context-aware column filtering mechanism, an intermediate SQL correction module that dynamically identifies and rectifies reasoning biases, and an enhanced SQL alignment and selection strategy. Additionally, we introduce BIRD-clear, a cleaned version of the BIRD dataset. Our model achieves execution accuracies of 74.45% and 76.41% on the BIRD development and test sets, respectively, surpassing the current state of the art. On BIRD-clear, it outperforms the baseline by 8.47 percentage points, demonstrating substantial improvements in both reliability and performance.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Text-to-SQL aims to translate natural language queries into SQL statements. Existing methods typically follow a pipeline of pre-processing, schema linking, candidate SQL generation, SQL alignment, and target SQL selection. However, these methods face significant challenges. First, they often struggle with column filtering during schema linking due to difficulties in comprehending raw metadata. Also, the candidate SQL generation process often suffers from reasoning errors, which limits accuracy improvements. To address these limitations, we propose a framework, called MCI-SQL, to efficiently and precisely generate SQL queries. Specifically, we assign metadata-complete contexts to each column, which significantly improves the accuracy of column filtering for schema linking. Also, for candidate SQL generation, we propose an intermediate correction mechanism that validates SQL queries and revises errors in a timely way. Moreover, we also propose effective optimizations in subsequent SQL alignment and selection phases, which further enhance the performance. Experiments on the widely-used BIRD benchmark show that MCI-SQL achieves execution accuracy of 74.45% on the development set and 76.41% on the test set, surpassing current published state-of-the-art results. In addition, we manually identify and correct 412 samples in the BIRD dataset, forming a new version named BIRD-clear, which is released together with our code on GitHub. We also evaluate our methods on BIRD-clear and find that MCI-SQL outperforms baselines by 8.47 percentage points in execution accuracy, further demonstrating the effectiveness and reliability of our framework.

Problem

• Text-to-SQL
• schema linking
• column filtering
• reasoning errors
• SQL generation

Innovation

• metadata-complete context
• intermediate correction
• schema linking
• Text-to-SQL
• execution accuracy