mlsanityData to 14 Oct 2026

Bootstrapping Learned Cost Models with Synthetic SQL Queries

arXiv 2508.19807 ↗First posted 27 Aug 2025cs.DB cs.AIcited by 0

On the map: Synthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping

Abstract (arXiv)

Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and performance. Recent advances in learned cost models have shown that when enough diverse SQL queries are available, one can effectively and efficiently predict the cost of running a given query against a specific database engine. In this paper, we describe our experience in exploiting modern synthetic data generation techniques, inspired by the generative AI and LLM community, to create high-quality datasets enabling the effective training of such learned cost models. Initial results show that we can improve a learned cost model's predictive accuracy by training it with 45% fewer queries than when using competitive generation approaches.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 9 of its 33 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

9 of 33 references.

References · 9

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  3. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
  4. 2019Neo: A Learned Query Optimizercited by 80
  5. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  6. 2023Lero: A Learning-to-Rank Query Optimizercited by 26
  7. 2022Zero-Shot Cost Models for Out-of-the-box Learned Cost Predictioncited by 16
  8. 2024The Unreasonable Effectiveness of LLMs for Query Optimizationcited by 4
  9. 2025A Learned Cost Model-based Cross-engine Optimizer for SQL Workloadscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
  2. 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
  3. 2025ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
  4. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
  5. 2025Thinkquel: A Model Dedicated to Text-to-dbt Using Synthetic Data and a Span-Aware Objective
  6. 2026Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents
  7. 2026RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems
  8. 2026CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation