Confidence Estimation for Text-to-SQL in Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maleki, Sepideh Entezari, Pourreza, Mohammadreza, Rafiei, Davood
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918127390949376
author Maleki, Sepideh Entezari
Pourreza, Mohammadreza
Rafiei, Davood
author_facet Maleki, Sepideh Entezari
Pourreza, Mohammadreza
Rafiei, Davood
contents Confidence estimation for text-to-SQL aims to assess the reliability of model-generated SQL queries without having access to gold answers. We study this problem in the context of large language models (LLMs), where access to model weights and gradients is often constrained. We explore both black-box and white-box confidence estimation strategies, evaluating their effectiveness on cross-domain text-to-SQL benchmarks. Our evaluation highlights the superior performance of consistency-based methods among black-box models and the advantage of SQL-syntax-aware approaches for interpreting LLM logits in white-box settings. Furthermore, we show that execution-based grounding of queries provides a valuable supplementary signal, improving the effectiveness of both approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Confidence Estimation for Text-to-SQL in Large Language Models
Maleki, Sepideh Entezari
Pourreza, Mohammadreza
Rafiei, Davood
Computation and Language
Databases
Confidence estimation for text-to-SQL aims to assess the reliability of model-generated SQL queries without having access to gold answers. We study this problem in the context of large language models (LLMs), where access to model weights and gradients is often constrained. We explore both black-box and white-box confidence estimation strategies, evaluating their effectiveness on cross-domain text-to-SQL benchmarks. Our evaluation highlights the superior performance of consistency-based methods among black-box models and the advantage of SQL-syntax-aware approaches for interpreting LLM logits in white-box settings. Furthermore, we show that execution-based grounding of queries provides a valuable supplementary signal, improving the effectiveness of both approaches.
title Confidence Estimation for Text-to-SQL in Large Language Models
topic Computation and Language
Databases
url https://arxiv.org/abs/2508.14056