mlsanityData to 7 Oct 2026

Efficient Guided Generation for Large Language Models

arXiv 2307.09702 ↗First posted 19 Jul 2023cs.CL cs.LGcited by 192

Not on the map. Why?

Cited by 34 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text generation with regular expressions and context-free grammars by allowing the construction of an index over a language model's vocabulary. The approach is model agnostic, allows one to enforce domain-specific knowledge and constraints, and enables the construction of reliable interfaces by guaranteeing the structure of the generated text. It adds little overhead to the token sequence generation process and significantly outperforms existing solutions. An implementation is provided in the open source Python library Outlines

Key facts. Cited by 192 papers in the map (data through 7 Oct 2026). Builds on 9 of its 21 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

9 of 21 references.

References · 9

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  4. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  5. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  6. 2017Abstract Syntax Networks for Code Generation and Semantic Parsingcited by 92
  7. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  8. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  9. 2022Validating Large Language Models with ReLMcited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 19; 2025: 45; 2026: 124.

192 papers.

Sort:

By area:

  1. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  2. 2023Large Language Models for Generative Information Extraction: A Surveycited by 183
  3. 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generationcited by 99
  4. 2025JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Modelscited by 66
  5. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Modelscited by 62
  6. 2024DeAL: Decoding-time Alignment for Large Language Modelscited by 55
  7. 2024Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Modelscited by 55
  8. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 45
  9. 2025Flexible and Efficient Grammar-Constrained Decodingcited by 42
  10. 2025Type-Constrained Code Generation with Language Modelscited by 32
  11. 2024Code Pretraining Improves Entity Tracking Abilities of Language Modelscited by 31
  12. 2025Enforcing Temporal Constraints for LLM Agentscited by 31
38 more
  1. 2024Adaptable Logical Control for Large Language Modelscited by 30
  2. 2025Steering LLM Thinking with Budget Guidancecited by 30
  3. 2024From Language Models over Tokens to Language Models over Characterscited by 28
  4. 2025AutoPDL: Automatic Prompt Optimization for LLM Agentscited by 27
  5. 2025Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Samplingcited by 20
  6. 2024An overview of domain-specific foundation model: key technologies, applications and challengescited by 19
  7. 2025Spotlight Your Instructions: Instruction-following with Dynamic Attention Steeringcited by 18
  8. 2025Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherencecited by 16
  9. 2025DINGO: Constrained Inference for Diffusion LLMscited by 15
  10. 2025Self-Steering Language Modelscited by 13
  11. 2024Controllable Generation via Locally Constrained Resamplingcited by 11
  12. 2025Efficient Test-Time Scaling for Small Vision-Language Modelscited by 11
  13. 2024Wordflow: Social Prompt Engineering for Large Language Modelscited by 9
  14. 2024Natural Language Outlines for Code: Literate Programming in the LLM Eracited by 9
  15. 2024Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammarscited by 8
  16. 2024Priority Sampling of Large Language Models for Compilerscited by 8
  17. 2024APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Promptscited by 8
  18. 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposalscited by 8
  19. 2024Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Reportcited by 7
  20. 2026The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decodingcited by 7
  21. 2023Informed Named Entity Recognition Decoding for Generative Language Modelscited by 6
  22. 2024Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mindcited by 6
  23. 2026Neuro-Symbolic Synergy for World Modelingcited by 6
  24. 2025RefineStat: Efficient Exploration for Probabilistic Program Synthesiscited by 5
  25. 2026Thinking Before Constraining: A Unified Decoding Framework for Large Language Modelscited by 5
  26. 2026PhysVid: Physics Aware Local Conditioning for Generative Video Modelscited by 5
  27. 2026Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systemscited by 5
  28. 2026this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a centcited by 5
  29. 2025Semantic Probabilistic Control of Language Modelscited by 4
  30. 2026On the Power of (Approximate) Reward Models for Inference-Time Scalingcited by 4
  31. 2026TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agentscited by 4
  32. 2026Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Ratecited by 4
  33. 2026The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Modelscited by 4
  34. 2026Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agentscited by 4
  35. 2024Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Usecited by 3
  36. 2025The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formatscited by 3
  37. 2025ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Searchcited by 3
  38. 2025Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMscited by 3

50 most cited of 192 All 192 (JSON)