mlsanityData to 7 Oct 2026

XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL

arXiv 2507.04701 ↗First posted 7 Jul 2025cs.CLcited by 40

Not on the map. Why?

Abstract (arXiv)

To leverage the advantages of LLM in addressing challenges in the Text-to-SQL task, we present XiYan-SQL, an innovative framework effectively generating and utilizing multiple SQL candidates. It consists of three components: 1) a Schema Filter module filtering and obtaining multiple relevant schemas; 2) a multi-generator ensemble approach generating multiple highquality and diverse SQL queries; 3) a selection model with a candidate reorganization strategy implemented to obtain the optimal SQL query. Specifically, for the multi-generator ensemble, we employ a multi-task fine-tuning strategy to enhance the capabilities of SQL generation models for the intrinsic alignment between SQL and text, and construct multiple generation models with distinct generation styles by fine-tuning across different SQL formats. The experimental results and comprehensive analysis demonstrate the effectiveness and robustness of our framework. Overall, XiYan-SQL achieves a new SOTA performance of 75.63% on the notable BIRD benchmark, surpassing all previous methods. It also attains SOTA performance on the Spider test set with an accuracy of 89.65%.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 41 of its 50 references that are in the map. First posted on arXiv 7 Jul 2025.

Builds on

41 of 50 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2024Qwen2.5 Technical Reportcited by 4,713
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  10. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  11. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  12. 2023LIMA: Less Is More for Alignmentcited by 1,080
29 more
  1. 2017A Survey on Multi-Task Learningcited by 838
  2. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  3. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  4. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  5. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  6. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  7. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  8. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  9. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  10. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  11. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  12. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  13. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  14. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  15. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  16. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  17. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  18. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  19. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  20. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  21. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  22. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  23. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  24. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  25. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  26. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 26
  27. 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applicationscited by 15
  28. 2024MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databasescited by 6
  29. 2024Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarioscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 31.

40 papers.

Sort:

By area:

  1. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scalingcited by 20
  2. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
  3. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 14
  4. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 8
  5. 2026PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agentscited by 5
  6. 2025A State-of-the-Art SQL Reasoning Model using RLVRcited by 4
  7. 2026RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolutioncited by 3
  8. 2026FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agentscited by 3
  9. 2025Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQLcited by 2
  10. 2025AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesiscited by 2
  11. 2026An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Datacited by 2
  12. 2026AgentNLQ: A General-Purpose Agent for Natural Language to SQLcited by 2
28 more
  1. 2025HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidancecited by 1
  2. 2025Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQLcited by 1
  3. 2026Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineeringcited by 1
  4. 2026R3-SQL: Ranking Reward and Resampling for Text-to-SQLcited by 1
  5. 2026Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewardscited by 1
  6. 2026SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestrationcited by 1
  7. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Modelscited by 0
  8. 2026Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databasescited by 0
  9. 2026SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesiscited by 0
  10. 2026Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQLcited by 0
  11. 2026LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Predictioncited by 0
  12. 2026Residual Skill Optimization for Text-to-SQL Ensemblescited by 0
  13. 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedbackcited by 0
  14. 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQLcited by 0
  15. 2026SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probingcited by 0
  16. 2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQLcited by 0
  17. 2026Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflowscited by 0
  18. 2026STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Datacited by 0
  19. 2026From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQLcited by 0
  20. 2026DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generationcited by 0
  21. 2026ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Modelscited by 0
  22. 2026ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQLcited by 0
  23. 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotationscited by 0
  24. 2026Replacing Training with Memory: Listwise Selection for Text-to-SQLcited by 0
  25. 2026DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learningcited by 0
  26. 2026BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligencecited by 0
  27. 2026Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysiscited by 0
  28. 2026Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQLcited by 0