Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

By Jinyang Li, Binyuan Hui, Ge Qu, Binhua Li, Jiaxi Yang, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng and 6 more. Neural Information Processing Systems, 2023

1,029 citations recorded by the source corpus.

Text-to-SQL parsing, which aims at converting natural language instructions into executable SQLs, has gained increasing attention in recent years. In particular, Codex and ChatGPT have shown impressive results in this task. However, most of the prevalent benchmarks, i.e., Spider, and WikiSQL, focus on database schema with few rows of database contents leaving the gap between academic study and real-world applications. To mitigate this gap, we present Bird, a big benchmark for large-scale database grounded in text-to-SQL tasks, containing 12,751 pairs of text-to-SQL data and 95 databases with a total size of 33.4 GB, spanning 37 professional domains. Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases. To solve these problems, text-to-SQL models must feature database value comprehension in addition to semantic parsing. The experimental results demonstrate the significance of database values in generating accurate text-to-SQLs for big databases. Furthermore, even the most effective text-to-SQL models, i.e. ChatGPT, only achieves 40.08% in execution accuracy, which is still far from the human result of 92.96%, proving that challenges still stand. Besides, we also provide an efficiency analysis to offer insights into generating text-to-efficient-SQLs that are beneficial to industries. We believe that BIRD will contribute to advancing real-world applications of text-to-SQL research. The leaderboard and source code are available: https://bird-bench.github.io/.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/8f831f341e959955a495730d81996e62c57cc0bd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

OpenHands: An Open Platform for AI Software Developers as Generalist Agents (2024, positive): “3% on a subset of BIRD, showcasing the potential of OpenHands as a SQL agent.”
AgentTuning: Enabling Generalized Agent Abilities for LLMs (2023, neutral): “In this section, we introduce our hybrid instruction-tuning strategy, aiming to enhance LLMs’ agent capabilities while keeping its general abilities.”
CodeS: Towards Building Open-source Language Models for Text-to-SQL (2024, positive): “We perform main experiments on two English text-to-SQL benchmarks: Spider [79] and BIRD [38].”
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation (2023, methodology): “Besides, to narrow the gap be-tween Text-to-SQL research and its real-world deployment, numerous large-scale benchmark datasets have been released, including WikiSQL [52], Spider [47], KaggleDBQA [18], BIRD [21] etc.”
Retrieval And Structuring Augmented Generation with Large Language Models (2025, unknown): “…remain in fully realizing RAS potential: efficient retrieval at scale [238, 314], maintaining high-quality knowledge representations [306], seamlessly integrating structured information with LLM reasoning [151, 230], and balancing computational overhead with real-time performance [48, 128].”
Griffin: Towards a Graph-Centric Relational Database Foundation Model (2025, unknown): “Numerous benchmarks have been proposed for comprehensive evaluation (Yu et al., 2018; Lei et al., 2024; Chen et al., 2019; Wu et al., 2024; Li et al., 2023; Qiu et al., 2024).”
Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval (2026, unknown): “…falls within this scope: text-to-SQL, long studied as a generation task on benchmarks such as WikiSQL (Zhong et al., 2017), Spider (Yu et al., 2018), and BIRD (Li et al., 2023b), is now also framed as retrieval, in which a question is matched against a collection of SQL statements or code snippets.”