ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL
Not on the map. Why?
Abstract (arXiv)
Large Language Models (LLMs) have demonstrated remarkable progress in translating natural language to SQL, but a significant semantic gap persists between their general knowledge and domain-specific semantics of databases. Historical translation logs constitute a rich source of this missing in-domain knowledge, where SQL queries inherently encapsulate real-world usage patterns of database schema. Existing methods primarily enhance the reasoning process for individual translations but fail to accumulate in-domain knowledge from past translations. We introduce ORANGE, an online self-evolutionary framework that constructs database-specific knowledge bases by parsing SQL queries from translation logs. By accumulating in-domain knowledge that contains schema and data semantics, ORANGE progressively reduces the semantic gap and enhances the accuracy of subsequent SQL translations. To ensure reliability, we propose a novel nested Chain-of-Thought SQL-to-Text strategy with tuple-semantic tracking, which reduces semantic errors during knowledge generation. Experiments on multiple benchmarks confirm the practicality of ORANGE, demonstrating its effectiveness for real-world Text-to-SQL deployment, particularly in handling complex and domain-specific queries.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 42 references that are in the map. First posted on arXiv 2 Nov 2025.
Builds on
38 of 42 references.
References · 38
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2023Teaching Large Language Models to Self-Debugcited by 963
- 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
- 2022Generating Sequences by Learning to Self-Correctcited by 271
26 more
- 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
- 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
- 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
- 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
- 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
- 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
- 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
- 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
- 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
- 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
- 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
- 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 44
- 2023ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systemscited by 42
- 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
- 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
- 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
- 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
- 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 26
- 2023Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generationcited by 24
- 2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21
- 2023Divide and Prompt: Chain of Thought Prompting for Text-to-SQLcited by 20
- 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
- 2024Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQLcited by 10
- 2023Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Promptingcited by 8
- 2024SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergycited by 7
- 2024Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQLcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
- 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
- 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
- 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
- 2026EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis
- 2024Multi-Turn Interactions for Text-to-SQL with Large Language Models
- 2025GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise
- 2026A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases