mlsanityData to 7 Oct 2026

CHESS: Contextual Harnessing for Efficient SQL Synthesis

arXiv 2405.16755 ↗First posted 27 May 2024cs.LG cs.AI cs.DBcited by 164

Not on the map. Why?

Cited by 33 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due to (i) the extensive size of database catalogs (descriptions of tables and their columns) and database values, (ii) reasoning over large database schemas, (iii) ensuring the functional validity of the generated queries, and (iv) navigating the ambiguities of natural language questions. We introduce CHESS, a Large Language Model (LLM) based multi-agent framework for efficient and scalable SQL synthesis, comprising four specialized agents, each targeting one of the aforementioned challenges: the Information Retriever (IR) extracts relevant data, the Schema Selector (SS) prunes large schemas, the Candidate Generator (CG) generates high-quality candidates and refines queries iteratively, and the Unit Tester (UT) validates queries through LLM-based natural language unit tests. Our framework offers configurable features that adapt to various deployment constraints, including 1) Supporting industrial-scale databases: leveraging the Schema Selector agent, CHESS efficiently narrows down very large database schemas into manageable sub-schemas, boosting system accuracy by approximately 2% and reducing the number of LLM tokens by × 5. 2) State-of-the-Art privacy-preserving performance: Among the methods using open-source models, CHESS achieves state-of-the-art performance, resulting in a high-performing, privacy-preserving system suitable for industrial deployment. 3) Scalablity with additional compute budget: In settings with high computational budgets, CHESS achieves 71.10% accuracy on the BIRD test set, within 2% of the leading proprietary method, while requiring approximately 83% fewer LLM calls.

Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). Builds on 26 of its 30 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

26 of 30 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  12. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
14 more
  1. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  2. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  3. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  4. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  5. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  6. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  7. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  8. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  9. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  10. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  11. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  12. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  13. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  14. 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 81; 2026: 62.

164 papers.

Sort:

By area:

  1. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  2. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  3. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  4. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  5. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  6. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  7. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  8. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  9. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
  10. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  11. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  12. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
38 more
  1. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 37
  2. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 34
  3. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 34
  4. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  5. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
  6. 2025ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedbackcited by 23
  7. 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQLcited by 22
  8. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  9. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLcited by 19
  10. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 17
  11. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  12. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
  13. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Mergingcited by 16
  14. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learningcited by 15
  15. 2025SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLcited by 15
  16. 2025ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigationcited by 15
  17. 2025AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scalecited by 15
  18. 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQLcited by 14
  19. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 14
  20. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
  21. 2025EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routingcited by 13
  22. 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuningcited by 13
  23. 2024FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmarkcited by 11
  24. 2024Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQLcited by 11
  25. 2025ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialectscited by 11
  26. 2025SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQLcited by 10
  27. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQLcited by 10
  28. 2024NAT-NL2GQL: A Novel Multi-Agent Framework for Translating Natural Language to Graph Query Languagecited by 9
  29. 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
  30. 2025Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQLcited by 9
  31. 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
  32. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  33. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 8
  34. 2024End-to-end Text-to-SQL Generation within an Analytics Insight Enginecited by 7
  35. 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanationscited by 7
  36. 2024DataLab: A Unified Platform for LLM-Powered Business Intelligencecited by 7
  37. 2025LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Modelscited by 7
  38. 2025LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoningcited by 7

50 most cited of 164 All 164 (JSON)