mlsanityData to 7 Oct 2026

Rationalization Models for Text-to-SQL

arXiv 2502.06759 ↗First posted 10 Feb 2025cs.CL cs.AI cs.DBcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing the final SQL query. The process begins with manually annotating a small set of examples, which are then used to prompt a large language model in an iterative, dynamic few-shot knowledge distillation procedure from a teacher model. A rationalization model is subsequently trained on the validated decomposed queries, enabling extensive synthetic CoT annotations for text-to-SQL datasets. To evaluate the approach, we fine-tune small language models with and without these rationales on the BIRD dataset. Results indicate that step-by-step query generation improves execution accuracy, especially for moderately and highly complex queries, while also enhancing explainability.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 30 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

21 of 30 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct
  2. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models14 Aug

Other references · 19

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Let's Verify Step by Stepcited by 3,598
  4. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  5. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2022Large Language Models Can Self-Improvecited by 656
  8. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  10. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  11. 2022Teaching Small Language Models to Reasoncited by 279
  12. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
7 more
  1. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  2. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  3. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  4. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  5. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  6. 2023Evaluating Cross-Domain Text-to-SQL Models and Benchmarkscited by 32
  7. 2025Extractive Schema Linking for Text-to-SQLcited by 13

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Modelscited by 0
  2. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL
  2. 2026Learning When to Reason for Text-to-SQL via SFT and DPO
  3. 2025JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament
  4. 2026LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
  5. 2024SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL
  6. 2025Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL
  7. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
  8. 2026Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning