MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gorti, Satya Krishna, Gofman, Ilan, Liu, Zhaoyan, Wu, Jiapeng, Vouitsis, Noël, Yu, Guangwei, Cresswell, Jesse C., Hosseinzadeh, Rasa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915153614733312
author Gorti, Satya Krishna
Gofman, Ilan
Liu, Zhaoyan
Wu, Jiapeng
Vouitsis, Noël
Yu, Guangwei
Cresswell, Jesse C.
Hosseinzadeh, Rasa
author_facet Gorti, Satya Krishna
Gofman, Ilan
Liu, Zhaoyan
Wu, Jiapeng
Vouitsis, Noël
Yu, Guangwei
Cresswell, Jesse C.
Hosseinzadeh, Rasa
contents Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at https://github.com/layer6ai-labs/msc-sql.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12916
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
Gorti, Satya Krishna
Gofman, Ilan
Liu, Zhaoyan
Wu, Jiapeng
Vouitsis, Noël
Yu, Guangwei
Cresswell, Jesse C.
Hosseinzadeh, Rasa
Computation and Language
Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at https://github.com/layer6ai-labs/msc-sql.
title MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
topic Computation and Language
url https://arxiv.org/abs/2410.12916