Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ramachandran, Ashwin, Sarawagi, Sunita
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916495935668224
author Ramachandran, Ashwin
Sarawagi, Sunita
author_facet Ramachandran, Ashwin
Sarawagi, Sunita
contents Calibration is crucial as large language models (LLMs) are increasingly deployed to convert natural language queries into SQL for commercial databases. In this work, we investigate calibration techniques for assigning confidence to generated SQL queries. We show that a straightforward baseline -- deriving confidence from the model's full-sequence probability -- outperforms recent methods that rely on follow-up prompts for self-checking and confidence verbalization. Our comprehensive evaluation, conducted across two widely-used Text-to-SQL benchmarks and multiple LLM architectures, provides valuable insights into the effectiveness of various calibration strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16742
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities
Ramachandran, Ashwin
Sarawagi, Sunita
Databases
Artificial Intelligence
Information Retrieval
Calibration is crucial as large language models (LLMs) are increasingly deployed to convert natural language queries into SQL for commercial databases. In this work, we investigate calibration techniques for assigning confidence to generated SQL queries. We show that a straightforward baseline -- deriving confidence from the model's full-sequence probability -- outperforms recent methods that rely on follow-up prompts for self-checking and confidence verbalization. Our comprehensive evaluation, conducted across two widely-used Text-to-SQL benchmarks and multiple LLM architectures, provides valuable insights into the effectiveness of various calibration strategies.
title Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities
topic Databases
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2411.16742