# Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL

arXiv: https://arxiv.org/abs/2607.03991 · HTML: https://mlsanity.com/paper/2607.03991/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs](https://mlsanity.com/paper/2305.11860/) (2023)
- [Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning](https://mlsanity.com/paper/2401.10480/) (2024)
- [MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL](https://mlsanity.com/paper/2406.12692/) (2024)
- [Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer](https://mlsanity.com/paper/2504.12589/) (2025)

## Built on by (most cited first, 1 of 1)

- [Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQL](https://mlsanity.com/paper/2609.25938/) (2026)

## Abstract (arXiv)

Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open question is when to stop, when the consistency has converged. We formulate this as a convergence-prediction problem and train a family of lightweight 1-D models that observe the running consistency trajectory and decide, at each step, whether further runs are unlikely to shift it materially, and we benchmark them against a principled Beta-Bernoulli stopping rule and a learned run-count baseline. On the BIRD benchmark and two production customer datasets, our method adapts its stopping point to each user question, halting sooner when consistency converges early and continuing longer when it converges late. We further show that the weak serial correlation between runs lets us permute their order as a training augmentation, controlled by a tunable shuffling weight. Performance stays consistent across the three datasets, and to mimic an imperfect production judge we inject noise into the correct/incorrect verdicts obtained by comparing the generated and ground-truth SQL results, showing that the method still predicts convergence reliably.