SOTAVerified

Text-To-SQL

Text-to-SQL is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.

( Image credit: SyntaxSQLNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 424 papers

TitleStatusHype
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language ModelsCode11
A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?Code5
XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLCode4
A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLCode4
Text2SQL is Not Enough: Unifying AI and Databases with TAGCode4
ExCoT: Optimizing Reasoning for Text-to-SQL with Execution FeedbackCode3
SuffixDecoding: Extreme Speculative Decoding for Emerging AI ApplicationsCode3
CHESS: Contextual Harnessing for Efficient SQL SynthesisCode3
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise RewardCode3
OmniSQL: Synthesizing High-quality Text-to-SQL Data at ScaleCode3
Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLCode3
Cognify: Supercharging Gen-AI Workflows With Hierarchical AutotuningCode3
RSL-SQL: Robust Schema Linking in Text-to-SQL GenerationCode2
CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement LearningCode2
Automatic database description generation for Text-to-SQLCode2
When is Tree Search Useful for LLM Planning? It Depends on the DiscriminatorCode2
E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLCode2
PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencyCode2
Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL GenerationCode2
Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationCode2
TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL GenerationCode2
CodeS: Towards Building Open-source Language Models for Text-to-SQLCode2
A Pilot Study for Chinese SQL Semantic ParsingCode2
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement LearningCode2
SeaD: End-to-end Text-to-SQL Generation with Schema-aware DenoisingCode2
Reasoning-Table: Exploring Reinforcement Learning for Table ReasoningCode2
SeqGenSQL -- A Robust Sequence Generation Model for Structured Query LanguageCode2
SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLCode2
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLCode2
Datrics Text2SQL. A Framework for Natural Language to SQL Query GenerationCode2
LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLCode2
Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health RecordsCode2
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL TaskCode2
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLCode2
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionCode2
A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilityCode1
GraPPa: Grammar-Augmented Pre-Training for Table Semantic ParsingCode1
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database QueriesCode1
A Study of In-Context-Learning-Based Text-to-SQL ErrorsCode1
Grounded Adaptation for Zero-shot Executable Semantic ParsingCode1
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL DialectsCode1
FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL BenchmarkCode1
ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT PipelinesCode1
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLCode1
EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health RecordsCode1
How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain SettingsCode1
CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-EditionsCode1
Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQLCode1
BookSQL: A Large Scale Text-to-SQL Dataset for Accounting DomainCode1
DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related QueriesCode1
Show:102550
← PrevPage 1 of 9Next →
All datasetsBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)spiderSpider 2.0SParCKaggleDBQASEDESQL-EvalText-To-SQL

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Human PerformanceExecution Accurarcy (Human)92.96—Unverified
2XiYan-SQLExecution Accuracy % (Test)75.63—Unverified
3DSAIR + GPT-4oExecution Accuracy % (Test)74.12—Unverified
4CHASE-SQL + GeminiExecution Accuracy % (Test)74.06—Unverified
5ExSL + granite-34b-codeExecution Accuracy % (Test)73.17—Unverified
6OpenSearch-SQL+ v2 + GPT-4oExecution Accuracy % (Test)72.28—Unverified
7Distillery + GPT-4oExecution Accuracy % (Test)71.83—Unverified
8Insights AIExecution Accuracy % (Test)70.26—Unverified
9PURPLE + RED + GPT-4oExecution Accuracy % (Test)70.21—Unverified
10MCTS-SQLExecution Accuracy % (Test)69.4—Unverified
#ModelMetricClaimedVerifiedStatus
1XiYan-SQLExecution Accuracy (Test)89.65—Unverified
2PET-SQLExecution Accuracy (Test)87.6—Unverified
3datagpt-sql-7B + InvalidSQL-FeedbackExecution Accuracy (Dev)87.2—Unverified
4DAIL-SQL + GPT-4 + Self-ConsistencyExecution Accuracy (Test)86.6—Unverified
5DIN-SQL + GPT-4Execution Accuracy (Test)85.3—Unverified
6datagpt-sql-7BExecution Accuracy (Dev)84.8—Unverified
7MSc-SQLExecution Accuracy (Test)84.7—Unverified
8MARLO + Claude 2.1Execution Accuracy (Test)84—Unverified
9C3 + ChatGPT + Zero-ShotExecution Accuracy (Test)82.3—Unverified
10code-davinci-002 175B (LEVER)Execution Accuracy (Dev)81.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Spider-Agent + o1-previewSuccess Rate17.03—Unverified
2Spider-Agent + GPT-4oSuccess Rate10.13—Unverified
3Spider-Agent + Claude-3.5-SonnectSuccess Rate9.02—Unverified
4Spider-Agent + GPT-4Success Rate8.86—Unverified
5Spider-Agent + Qwen2.5-72BSuccess Rate6.17—Unverified
6Spider-Agent + DeepSeek-V2.5Success Rate5.22—Unverified
7Spider-Agent + Gemini-Pro-1.5Success Rate2.53—Unverified
8Spider-Agent + Llama-3.1-405BSuccess Rate2.21—Unverified
#ModelMetricClaimedVerifiedStatus
1RASAT+PICARDinteraction match accuracy45.2—Unverified
2RAT-SQL-TC + GAPinteraction match accuracy43.2—Unverified
3HIE-SQL + GraPPainteraction match accuracy42.9—Unverified
4RAT-SQL + SCoReinteraction match accuracy38.1—Unverified
5EditSQL + BERTinteraction match accuracy25.3—Unverified
6GAZP + BERTinteraction match accuracy23.5—Unverified
7SyntaxSQL-coninteraction match accuracy5.2—Unverified
#ModelMetricClaimedVerifiedStatus
1RAT-SQLExact Match (EM)26.77—Unverified
2Edit-SQLExact Match (EM)11.73—Unverified
#ModelMetricClaimedVerifiedStatus
1T5-LargePCM-F1 (dev)48.2—Unverified
#ModelMetricClaimedVerifiedStatus
1XiYan-SQLExecution Accuracy69.86—Unverified
#ModelMetricClaimedVerifiedStatus
1Orange-mini0-shot MRR74.17—Unverified