mlsanityData to 14 Oct 2026

Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning

arXiv 2505.14174 ↗First posted 20 May 2025cs.CL cs.LGcited by 13

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

Abstract (arXiv)

LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM techniques including Chain-of-Thought (CoT), self-consistency, and fine-tuning. These methods can be costly at inference time, sometimes requiring over a hundred LLM calls with reasoning, incurring average costs of up to 0.46 per query, while fine-tuning models can cost thousands of dollars. We introduce "N-rep" consistency, a more cost-efficient text-to-SQL approach that achieves similar BIRD benchmark scores as other more expensive methods, at only 0.039 per query. N-rep leverages multiple representations of the same schema input to mitigate weaknesses in any single representation, making the solution more robust and allowing the use of smaller and cheaper models without any reasoning or fine-tuning. To our knowledge, N-rep is the best-performing text-to-SQL approach in its cost range.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 10 of its 21 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

10 of 21 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL29 Mar
  2. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models14 Aug

Other references · 8

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  6. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  7. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  8. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 11.

13 papers.

Sort:

By area:

  1. 2026Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboardscited by 13
  2. 2025Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domaincited by 4
  3. 2025SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verificationcited by 4
  4. 2026RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolutioncited by 3
  5. 2026SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraintscited by 1
  6. 2026Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineeringcited by 1
  7. 2026SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluationcited by 1
  8. 2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQLcited by 0
  9. 2026SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQLcited by 0
  10. 2026Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQLcited by 0
  11. 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotationscited by 0
  12. 2026Replacing Training with Memory: Listwise Selection for Text-to-SQLcited by 0
1 more
  1. 2026BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs
  2. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
  3. 2026LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
  4. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
  5. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
  6. 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generation
  7. 2025Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL
  8. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL