Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Text-to-SQL aims to translate natural language questions into executable SQL queries over structured databases, enabling non-expert users to access data intuitively. While recent advances in large language models (LLMs) have shown promise in this task, existing LLM-based approaches often struggle to strike a balance between strong reasoning capabilities and robust generalization. To address these limitations, we propose CoTE-SQL to enhance the LLM-based text-to-SQL generation with three key innovations: (i) self-enhanced reasoning traces distilled from LLMs without human annotation, (ii) structured chain-of-thought (CoT) prompting with modular decomposition and examples retrieval, and (iii) error-aware revision based on SQL execution feedback. Extensive experiments on the Spider and Bird benchmarks demonstrate that CoTE-SQL achieves new state-of-the-art performance among methods built on open-source LLMs with comparable model sizes on Bird (53.39% EX / 59.02 VES) and strong results on Spider (79.60% EX / 77.19 VES), with especially significant gains on complex queries. Results highlight the effectiveness of combining self-enhancement, structured reasoning, and execution-time feedback within an LLM-based framework for text-to-SQL design.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 52 references that are in the map. First posted on arXiv 14 Jun 2026.
Builds on
18 of 52 references.
Closest ancestors · 6
Same direction, newest first
- 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning19 May
- 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL29 Mar
- 2025ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback25 Mar
- 2025Rationalization Models for Text-to-SQL10 Feb
- 2024PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL21 Sep
- 2024SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL16 Sep
Other references · 12
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2024Qwen2.5 Technical Reportcited by 4,942
- 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2025NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translationcited by 33
- 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 19
- 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruningcited by 16
- 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanationscited by 8
- 2024DAC: Decomposed Automation Correction for Text-to-SQLcited by 6
- 2026IQuest-Coder-V1 Technical Reportcited by 6
- 2024Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurementcited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Lucy: Think and Reason to Solve Text-to-SQL
- 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs
- 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
- 2025RAISE: Reasoning Agent for Interactive SQL Exploration
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL
- 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL
- 2024Multi-Turn Interactions for Text-to-SQL with Large Language Models
- 2024Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models