mlsanityData to 7 Oct 2026

Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

arXiv 1704.07138 ↗First posted 24 Apr 2017cs.CLcited by 234

Not on the map. Why?

Abstract (arXiv)

We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model that generates a sequence mathbfhaty = y0ldots yT , by maximizing p(y | x) = prodlimitstp(yt | x; y0 ldots yt-1) . Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate additional knowledge into a model's output without requiring any modification of the model parameters or training data. We demonstrate the feasibility and flexibility of Lexically Constrained Decoding by conducting experiments on Neural Interactive-Predictive Translation, as well as Domain Adaptation for Neural Machine Translation. Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, GBS can be used to achieve significant gains in performance in domain adaptation scenarios.

Key facts. Cited by 234 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 39; 2023: 49; 2024: 34; 2025: 32; 2026: 42.

234 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  3. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 186
  4. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  5. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  6. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  7. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  8. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  9. 2023Amortizing intractable inference in large language modelscited by 94
  10. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  11. 2024Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Differencecited by 85
  12. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
38 more
  1. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  2. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  3. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
  4. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 67
  5. 2023Adaptive Machine Translation with Large Language Modelscited by 58
  6. 2021A Plug-and-Play Method for Controlled Text Generationcited by 55
  7. 2022Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptionscited by 54
  8. 2024Grammar-Aligned Decodingcited by 54
  9. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  10. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  11. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  12. 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
  13. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  14. 2024A Comprehensive Survey on Data Augmentationcited by 38
  15. 2021Guided Generation of Cause and Effectcited by 33
  16. 2023Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuningcited by 33
  17. 2022Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysiscited by 30
  18. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  19. 2023DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelinescited by 27
  20. 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
  21. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  22. 2022Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Featurescited by 24
  23. 2022Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Searchcited by 23
  24. 2023Mixture of Soft Prompts for Controllable Data Generationcited by 23
  25. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  26. 2023Interactive AI Alignment: Specification, Process, and Evaluation Alignmentcited by 22
  27. 2025FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Samplingcited by 20
  28. 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
  29. 2022Why is constrained neural language generation particularly challenging?cited by 19
  30. 2024DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inferencecited by 19
  31. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  32. 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Modelscited by 17
  33. 2024Permute-and-Flip: An optimally stable and watermarkable decoder for LLMscited by 17
  34. 2023Chain-of-Dictionary Prompting Elicits Translation in Large Language Modelscited by 16
  35. 2021On the Evaluation of Machine Translation for Terminology Consistencycited by 15
  36. 2022Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extractioncited by 15
  37. 2023Formally Specifying the High-Level Behavior of LLM-Based Agentscited by 15
  38. 2022Factual and Informative Review Generation for Explainable Recommendationcited by 14

50 most cited of 234 All 234 (JSON)