PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Wei, Li, Guoliang, Wang, Haoyu, Han, Yuxing, Wu, Xufei, Wu, Fan, Zhou, Xuanhe
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908562781896704
author Zhou, Wei
Li, Guoliang
Wang, Haoyu
Han, Yuxing
Wu, Xufei
Wu, Fan
Zhou, Xuanhe
author_facet Zhou, Wei
Li, Guoliang
Wang, Haoyu
Han, Yuxing
Wu, Xufei
Wu, Fan
Zhou, Xuanhe
contents Large language models (LLMS) have shown increasing effectiveness in Text-to-SQL tasks. However, another closely related problem, Cross-System SQL Translation (a.k.a., SQL-to-SQL), which adapts a query written for one database system (e.g., MySQL) into its equivalent one for another system (e.g., ClickHouse), is of great practical importance but remains underexplored. Existing SQL benchmarks are not well-suited for SQL-to-SQL evaluation, which (1) focus on a limited set of database systems (often just SQLite) and (2) cannot capture many system-specific SQL dialects (e.g., customized functions, data types, and syntax rules). Thus, in this paper, we introduce PARROT, a Practical And Realistic BenchmaRk for CrOss-System SQL Translation. PARROT comprises 598 translation pairs from 38 open-source benchmarks and real-world business services, specifically prepared to challenge system-specific SQL understanding (e.g., LLMS achieve lower than 38.53% accuracy on average). We also provide multiple benchmark variants, including PARROT-Diverse with 28,003 translations (for extensive syntax testing) and PARROT-Simple with 5,306 representative samples (for focused stress testing), covering 22 production-grade database systems. To promote future research, we release a public leaderboard and source code at: https://code4db.github.io/parrot-bench/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23338
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
Zhou, Wei
Li, Guoliang
Wang, Haoyu
Han, Yuxing
Wu, Xufei
Wu, Fan
Zhou, Xuanhe
Databases
Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
Large language models (LLMS) have shown increasing effectiveness in Text-to-SQL tasks. However, another closely related problem, Cross-System SQL Translation (a.k.a., SQL-to-SQL), which adapts a query written for one database system (e.g., MySQL) into its equivalent one for another system (e.g., ClickHouse), is of great practical importance but remains underexplored. Existing SQL benchmarks are not well-suited for SQL-to-SQL evaluation, which (1) focus on a limited set of database systems (often just SQLite) and (2) cannot capture many system-specific SQL dialects (e.g., customized functions, data types, and syntax rules). Thus, in this paper, we introduce PARROT, a Practical And Realistic BenchmaRk for CrOss-System SQL Translation. PARROT comprises 598 translation pairs from 38 open-source benchmarks and real-world business services, specifically prepared to challenge system-specific SQL understanding (e.g., LLMS achieve lower than 38.53% accuracy on average). We also provide multiple benchmark variants, including PARROT-Diverse with 28,003 translations (for extensive syntax testing) and PARROT-Simple with 5,306 representative samples (for focused stress testing), covering 22 production-grade database systems. To promote future research, we release a public leaderboard and source code at: https://code4db.github.io/parrot-bench/.
title PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
topic Databases
Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2509.23338