RSL-SQL: Robust Schema Linking in Text-to-SQL Generation

2024/10/31 by Cao, Zhenbiao, Zhihao Fan, Zheng, Yuanlei +6 · 14 citations
Computer Science · #Advanced Database Systems and Queries #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #FOS: Computer and information sciences #Logic, programming, and type systems #Mathematics, Computing, and Information Processing

paper · pdf · doi:10.48550/arxiv.2411.00073

openalex publication_date 2024/10/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant schema elements, therefore reducing noise and computational overhead. However, schema linking faces risks that require caution, including the potential omission of necessary elements and disruption of database structural integrity. To address these challenges, we propose a novel framework called RSL-SQL that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. We improve the recall of pattern linking using forward and backward pruning methods, achieving a strict recall of 94% while reducing the number of input columns by 83%. Furthermore, it hedges the risk by voting between a full mode and a simplified mode enhanced with contextual information. Experiments on the BIRD and Spider benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on Spider using GPT-4o. Furthermore, our approach outperforms a series of GPT-4 based Text-to-SQL systems when adopting DeepSeek (much cheaper) with same intact prompts. Extensive analysis and ablation studies confirm the effectiveness of each component in our framework. The codes are available at https://github.com/Laqcce-cao/RSL-SQL.

Cited by

• Hallucination Detection for LLM-based Text-to-SQL Generation via Two-Stage Metamorphic Testing
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
• AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
• AskDB: An LLM Agent for Natural Language Interaction with Relational Databases
• Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
• BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
• ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL
• SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
• MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
• Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL
• BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions
• SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
• GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL
• SLM-SQL: An Exploration of Small Language Models for Text-to-SQL

Related

• The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models
• Reliable Text-to-SQL with Adaptive Abstention
• LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction
• SQL-to-Schema Enhances Schema Linking in Text-to-SQL
• SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases