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

Showing 201250 of 424 papers

TitleStatusHype
Data Transformation to Construct a Dataset for Generating Entity-Relationship Model from Natural Language0
dIR -- Discrete Information Retrieval: Conversational Search over Unstructured (and Structured) Data with Large Language Models0
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLCode2
LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?Code0
Decoupling SQL Query Hardness Parsing for Text-to-SQL0
Domain Adaptation of a State of the Art Text-to-SQL Model: Lessons Learned and Challenges Found0
DBCopilot: Natural Language Querying over Massive Databases via Schema RoutingCode1
A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases0
SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data0
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLCode1
Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domain0
ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL0
SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL TranslationCode0
Evaluating Cross-Domain Text-to-SQL Models and Benchmarks0
Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey0
ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-ThoughtCode1
TUR2SQL: A Cross-Domain Turkish Dataset For Text-to-SQLCode0
Benchmarking and Improving Text-to-SQL Generation under AmbiguityCode0
Semantic Decomposition of Question and SQL for Text-to-SQL ParsingCode0
MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel InterpretationsCode0
Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison0
Selective Demonstrations for Cross-domain Text-to-SQLCode0
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?Code1
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense RetrievalCode0
Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationCode2
Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting0
C3: Zero-shot Text-to-SQL with ChatGPTCode1
Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain0
T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic ParsingCode0
Correcting Semantic Parses with Natural Language through Dynamic Schema EncodingCode0
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing0
Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based TechniquesCode1
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)0
Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New AlgorithmsCode0
CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical DatasetCode0
UNITE: A Unified Benchmark for Text-to-SQL EvaluationCode1
Uncovering and Categorizing Social Biases in Text-to-SQLCode0
Exploring Chain-of-Thought Style Prompting for Text-to-SQL0
Error Detection for Text-to-SQL Semantic ParsingCode0
Text-to-SQL Error Correction with Language Models of CodeCode1
Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies0
How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain SettingsCode1
Learning to Simulate Natural Language Feedback for Interactive Semantic ParsingCode1
Interactive Text-to-SQL Generation via Editable Step-by-Step ExplanationsCode1
QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing0
SPSQL: Step-by-step Parsing Based Framework for Text-to-SQL Generation0
Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing0
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLsCode1
Controllable Data Augmentation for Context-Dependent Text-to-SQL0
Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval0
Show:102550
← PrevPage 5 of 9Next →

Benchmark Results

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