Data to 7 Oct 2026

Robust Text-to-SQL Generation with Execution-Guided Decoding

arXiv 1807.03100 ↗First posted 9 Jul 2018cs.CL cs.AI cs.DBcited by 51

Not on the map. Why?

Abstract (arXiv)

We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty programs during the decoding procedure by conditioning on the execution of partially generated program. The mechanism can be used with any autoregressive generative model, which we demonstrate on four state-of-the-art recurrent or template-based semantic parsing models. We demonstrate that execution guidance universally improves model performance on various text-to-SQL datasets with different scales and query complexity: WikiSQL, ATIS, and GeoQuery. As a result, we achieve new state-of-the-art execution accuracy of 83.8% on WikiSQL.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 4; 2024: 9; 2025: 6; 2026: 13.

51 papers.

Sort:

By area:

2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
2024NExT: Teaching Large Language Models to Reason about Code Executioncited by 60
2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
2022Reasoning Like Program Executorscited by 45
2022A Survey on Table Question Answering: Recent Advancescited by 41
2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutionscited by 38

38 more

2021SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcited by 27
2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
2025Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewardscited by 25
2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQLcited by 22
2022PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generationcited by 16
2022GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representationcited by 13
2022Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Surveycited by 11
2023Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasetscited by 9
2021Learning from Executions for Semantic Parsingcited by 7
2024Grounding Data Science Code Generation with Input-Output Specificationscited by 7
2024End-to-end Text-to-SQL Generation within an Analytics Insight Enginecited by 7
2022Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsingcited by 5
2024Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQLcited by 5
2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
2026EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolutioncited by 5
2022From Examples to Rules: Neural Guided Rule Synthesis for Information Extractioncited by 4
2025GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprisecited by 4
2025Valid Text-to-SQL Generation with Unification-based DeepStochLogcited by 3
2022Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generationcited by 2
2023Decoupling SQL Query Hardness Parsing for Text-to-SQLcited by 1
2024Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threatscited by 1
2024Semantic Parsing with Candidate Expressions for Knowledge Base Question Answeringcited by 1
2026FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Usecited by 1
2026CYGNET: Cypher Gate for Neural Execution Triage and Cost Containmentcited by 1
2026PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agentscited by 1
2026BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQLcited by 1
2026Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baselinecited by 1
2021Self-supervised Text-to-SQL Learning with Header Alignment Trainingcited by 0
2022Searching for Better Database Queries in the Outputs of Semantic Parserscited by 0
2024EzSQL: An SQL intermediate representation for improving SQL-to-text Generationcited by 0
2025LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQLcited by 0
2026PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systemscited by 0
2026Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQLcited by 0
2026CLARA: Clarification of Language Ambiguity through Result Analysis for Natural-Language Cancer Genomics Queriescited by 0
2026SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Datacited by 0
2026Beyond the Harness: End-to-End Optimization of Context Artifacts for Enterprise Text-to-SQLcited by 0
2026What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Frameworkcited by 0

50 most cited of 51 All 51 (JSON)