mlsanityData to 7 Oct 2026

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

arXiv 2109.05093 ↗First posted 10 Sep 2021cs.CL cs.PLcited by 402

Not on the map. Why?

Cited by 27 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.

Key facts. Cited by 402 papers in the map (data through 7 Oct 2026). Builds on 15 of its 20 references that are in the map. First posted on arXiv 10 Sep 2021.

Builds on

15 of 20 references.

References · 15

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  3. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  4. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  5. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  6. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  7. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  8. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  9. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  10. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  11. 2018TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generationcited by 88
  12. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
3 more
  1. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  2. 2020Optimizing Deeper Transformers on Small Datasetscited by 41
  3. 2019Grammar-based Neural Text-to-SQL Generationcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 54; 2023: 88; 2024: 78; 2025: 64; 2026: 113.

402 papers.

Sort:

By area:

  1. 2023Teaching Large Language Models to Self-Debugcited by 963
  2. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  3. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  4. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  5. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  6. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  7. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  8. 2022Binding Language Models in Symbolic Languagescited by 224
  9. 2023Efficient Guided Generation for Large Language Modelscited by 192
  10. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  11. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 186
  12. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
38 more
  1. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  2. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  3. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  4. 2022Natural Language to Code Translation with Executioncited by 122
  5. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  6. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  7. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  8. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  9. 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generationcited by 99
  10. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  11. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  12. 2022MapQA: A Dataset for Question Answering on Choropleth Mapscited by 82
  13. 2023AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZcited by 74
  14. 2024XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Modelscited by 73
  15. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  16. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  17. 2024SynCode: LLM Generation with Grammar Augmentationcited by 66
  18. 2025JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Modelscited by 66
  19. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  20. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 62
  21. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  22. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  23. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  24. 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
  25. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  26. 2022Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptionscited by 54
  27. 2024Grammar-Aligned Decodingcited by 54
  28. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  29. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  30. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  31. 2021Few-Shot Semantic Parsing with Language Models Trained On Codecited by 50
  32. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  33. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 50
  34. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  35. 2024Automata-based constraints for language model decodingcited by 49
  36. 2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
  37. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  38. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46

50 most cited of 402 All 402 (JSON)