mlsanityData to 7 Oct 2026

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics

arXiv 2112.08726 ↗First posted 16 Dec 2021cs.CLcited by 153

Not on the map. Why?

Abstract (arXiv)

The dominant paradigm for neural text generation is left-to-right decoding from autoregressive language models. Constrained or controllable generation under complex lexical constraints, however, requires foresight to plan ahead feasible future paths. Drawing inspiration from the A* search algorithm, we propose NeuroLogic A*esque, a decoding algorithm that incorporates heuristic estimates of future cost. We develop efficient lookahead heuristics that are efficient for large-scale language models, making our method a drop-in replacement for common techniques such as beam search and top-k sampling. To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction. Our approach outperforms competitive baselines on five generation tasks, and achieves new state-of-the-art performance on table-to-text generation, constrained machine translation, and keyword-constrained generation. The improvements are particularly notable on tasks that require complex constraint satisfaction or in few-shot or zero-shot settings. NeuroLogic A*esque illustrates the power of decoding for improving and enabling new capabilities of large-scale language models.

Key facts. Cited by 153 papers in the map (data through 7 Oct 2026). Builds on 33 of its 67 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

33 of 67 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  5. 2018Hierarchical Neural Story Generationcited by 1,182
  6. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
  7. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  8. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  9. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  10. 2017Toward Controlled Generation of Textcited by 271
  11. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  12. 2017Challenges in Data-to-Document Generationcited by 226
21 more
  1. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  2. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  3. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  4. 2016Guided Open Vocabulary Image Captioning with Constrained Beam Searchcited by 105
  5. 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
  6. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  7. 2019Comparison of Diverse Decoding Methods from Conditional Language Modelscited by 78
  8. 2020The Radicalization Risks of GPT-3 and Advanced Neural Language Modelscited by 76
  9. 2019Training Neural Machine Translation To Apply Terminology Constraintscited by 73
  10. 2019Non-Monotonic Sequential Text Generationcited by 55
  11. 2021Machine Translation Decoding beyond Beam Searchcited by 55
  12. 2020Best-First Beam Searchcited by 40
  13. 2018Neural Machine Translation Decoding with Terminology Constraintscited by 36
  14. 2019Pragmatically Informative Text Generationcited by 32
  15. 2017Recurrent Neural Networks as Weighted Language Recognizerscited by 30
  16. 2018Findings of the E2E NLG Challengecited by 28
  17. 2016Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Stringscited by 27
  18. 2016Multi-domain Neural Network Language Generation for Spoken Dialogue Systemscited by 18
  19. 2020Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Modelscited by 9
  20. 2020Opportunistic Decoding with Timely Correction for Simultaneous Translationcited by 8
  21. 2016Global Neural CCG Parsing with Optimality Guaranteescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 21; 2023: 53; 2024: 42; 2025: 17; 2026: 20.

153 papers.

Sort:

By area:

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decodingcited by 295
  3. 2022Generating Sequences by Learning to Self-Correctcited by 271
  4. 2022A Contrastive Framework for Neural Text Generationcited by 224
  5. 2023Planning with Large Language Models for Code Generationcited by 179
  6. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 162
  7. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  8. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planningcited by 135
  9. 2023Controlled Decoding from Language Modelscited by 133
  10. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  11. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  12. 2023Amortizing intractable inference in large language modelscited by 94
38 more
  1. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  2. 2024Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Differencecited by 85
  3. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  4. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  5. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  6. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
  7. 2023Tractable Control for Autoregressive Language Generationcited by 65
  8. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64
  9. 2022Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planningcited by 59
  10. 2023Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingcited by 59
  11. 2024DeAL: Decoding-time Alignment for Large Language Modelscited by 55
  12. 2024Grammar-Aligned Decodingcited by 54
  13. 2023See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoningcited by 49
  14. 2023From task structures to world models: What do LLMs know?cited by 46
  15. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 45
  16. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  17. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 43
  18. 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
  19. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  20. 2024DeepEdit: Knowledge Editing as Decoding with Constraintscited by 33
  21. 2023Faithfulness-Aware Decoding Strategies for Abstractive Summarizationcited by 31
  22. 2024Adaptable Logical Control for Large Language Modelscited by 30
  23. 2023Elastic Weight Removal for Faithful and Abstractive Dialogue Generationcited by 29
  24. 2022I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervisioncited by 26
  25. 2023Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learningcited by 26
  26. 2024Non-myopic Generation of Language Models for Reasoning and Planningcited by 25
  27. 2023Generating Summaries with Controllable Readability Levelscited by 24
  28. 2024SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Modelscited by 22
  29. 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraintscited by 21
  30. 2024LiSeCo: Linear Semantic Control for Language Generationcited by 20
  31. 2025Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Samplingcited by 20
  32. 2024DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inferencecited by 19
  33. 2022Controllable Text Generation with Language Constraintscited by 18
  34. 2023Adaptive and Personalized Exercise Generation for Online Language Learningcited by 18
  35. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  36. 2022Penguins Don't Fly: Reasoning about Generics through Instantiations and Exceptionscited by 17
  37. 2024Permute-and-Flip: An optimally stable and watermarkable decoder for LLMscited by 17
  38. 2025Constrained Discrete Diffusioncited by 16

50 most cited of 153 All 153 (JSON)