mlsanityData to 14 Oct 2026

Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL

arXiv 2510.14296 ↗First posted 16 Oct 2025cs.CL cs.IRcited by 4

Not on the map. Why?

Abstract (arXiv)

Schema linking -- the process of aligning natural language questions with database schema elements -- is a critical yet underexplored component of Text-to-SQL systems. While recent methods have focused primarily on improving SQL generation, they often neglect the retrieval of relevant schema elements, which can lead to hallucinations and execution failures. In this work, we propose a context-aware bidirectional schema retrieval framework that treats schema linking as a standalone problem. Our approach combines two complementary strategies: table-first retrieval followed by column selection, and column-first retrieval followed by table selection. It is further augmented with techniques such as question decomposition, keyword extraction, and keyphrase extraction. Through comprehensive evaluations on challenging benchmarks such as BIRD and Spider, we demonstrate that our method significantly improves schema recall while reducing false positives. Moreover, SQL generation using our retrieved schema consistently outperforms full-schema baselines and closely approaches oracle performance, all without requiring query refinement. Notably, our method narrows the performance gap between full and perfect schema settings by 50%. Our findings highlight schema linking as a powerful lever for enhancing Text-to-SQL accuracy and efficiency.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 40 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

32 of 40 references.

References · 32

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  4. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  6. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  7. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  8. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  9. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 138
  10. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
  11. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 105
  12. 2024Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systemscited by 87
20 more
  1. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  2. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  3. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  4. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
  5. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  6. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  7. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  8. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  9. 2023CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLcited by 24
  10. 2024Large Language Model Enhanced Text-to-SQL Generation: A Surveycited by 24
  11. 2025ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedbackcited by 24
  12. 2022Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graphcited by 22
  13. 2024H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tablescited by 21
  14. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 19
  15. 2024NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalizationcited by 16
  16. 2025Extractive Schema Linking for Text-to-SQLcited by 13
  17. 2024SQL-to-Schema Enhances Schema Linking in Text-to-SQLcited by 12
  18. 2024Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQLcited by 11
  19. 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
  20. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQLcited by 11
  2. 2026Fine-Grained Table Retrieval Through the Lens of Complex Queriescited by 1
  3. 2026Schema-First Retrieval: Embedding Catalogs for Natural Language Analyticscited by 1
  4. 2026DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generationcited by 0