Natural language to SQL: Where are we today?

Summary: NL2SQL: a unified, large-scale evaluation of eleven NL2SQL methods over 10+ benchmarks (WTQ, TPC-H). Taxonomy, error analysis, and a practical validation tool reveal dataset/metric flaws and outline paths toward real-world applicability. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 12076
Venue: VLDB
Year: 2020
Pagerank: 0.00014857465
Overall Rank: 984 | 93.16%
DOI: 10.14778/3401960.3401970

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 25 of 25 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,541	Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes	2023	CIDR	0.00011456579
1,732	CatSQL: Towards Real World Natural Language to SQL Applications	2023	VLDB	0.00010732004
3,501	MT-TeQL: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations	2022	VLDB	7.0366785e-05
3,876	The Design of an LLM-powered Unstructured Analytics System	2025	CIDR	6.6741456e-05
4,687	Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures	2023	VLDB	5.9986055e-05
4,825	Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks	2021	SIGMOD	5.8946721e-05
5,780	MOCHA: A Tool for Visualizing Impact of Operator Choices in Query Execution Plans for Database Education	2022	VLDB	5.3298375e-05
8,155	Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study	2024	SIGMOD	4.5745248e-05
8,990	Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans	2021	SIGMOD	4.413295e-05
9,032	Sphinteract: Resolving Ambiguities in NL2SQL Through User Interaction	2025	VLDB	4.4039656e-05
9,035	Data-Driven Insight Synthesis for Multi-Dimensional Data	2024	VLDB	4.4039656e-05
9,151	The Power of Constraints in Natural Language to SQL Translation	2025	VLDB	4.3849295e-05
9,402	CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models	2024	SIGMOD	4.3441378e-05
9,408	Experimental Analysis of Large-scale Learnable Vector Storage Compression	2024	VLDB	4.3441378e-05
9,929	Wred: Workload Reduction for Scalable Index Tuning	2024	SIGMOD	4.2510122e-05
10,249	TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries	2026	VLDB	4.1945683e-05
10,475	Cracking SQL Barriers: An LLM-based Dialect Translation System	2025	SIGMOD	4.1945683e-05
10,754	OmniMatch: Joinability Discovery in Data Products	2025	VLDB	4.1945683e-05
10,784	Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models	2025	VLDB	4.1945683e-05
10,897	Welding Natural Language Queries to Analytics IRs with LLMs	2024	CIDR	4.1945683e-05
11,035	Relational Query Synthesis ⋈ Decision Tree Learning	2024	VLDB	4.1945683e-05
11,058	LLM-PBE: Assessing Data Privacy in Large Language Models	2024	VLDB	4.1945683e-05
11,349	LANTERN: Boredom-conscious Natural Language Description Generation of Query Execution Plans for Database Education	2022	SIGMOD	4.1945683e-05
11,506	Robust Voice Querying with MUVE: Optimally Visualizing Results of Phonetically Similar Queries	2021	VLDB	4.1945683e-05
11,540	DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks	2021	VLDB	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
206	Constructing an Interactive Natural Language Interface for Relational Databases	2015	VLDB	0.00034667032
535	ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores	2016	VLDB	0.00020727678
1,057	Cosette: An Automated Prover for SQL	2017	CIDR	0.0001439886
2,099	Axiomatic Foundations and Algorithms for Deciding Semantic Equivalences of SQL Queries	2018	VLDB	9.5479391e-05
2,816	DBPal: A Learned NL-Interface for Databases	2018	SIGMOD	8.0694738e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
5,353	An In-Depth Benchmarking of Text-to-SQL Systems	2021	SIGMOD	5.5521332e-05
3,501	MT-TeQL: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations	2022	VLDB	7.0366785e-05
3,635	A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems	2021	SIGMOD	6.8981006e-05
6,826	Natural Language Interfaces for Databases with Deep Learning	2023	VLDB	4.9142824e-05
1,732	CatSQL: Towards Real World Natural Language to SQL Applications	2023	VLDB	0.00010732004
10,221	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB	4.1945683e-05
2,321	DBPal: A Fully Pluggable NL2SQL Training Pipeline	2020	SIGMOD	9.03609e-05
3,662	The Dawn of Natural Language to SQL: Are We Fully Ready?	2024	VLDB	6.8672143e-05
2,988	NL2SQL is a solved problem... Not!	2024	CIDR	7.7761714e-05
10,837	Natural Language to SQL: State of the Art and Open Problems	2025	VLDB	4.1945683e-05