mlsanityData to 7 Oct 2026

Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

arXiv 1804.06609 ↗First posted 18 Apr 2018cs.CLcited by 181

Not on the map. Why?

Abstract (arXiv)

The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or guided decoding, a modification to beam search that forces the inclusion of pre-specified words and phrases in the output. However, while theoretically sound, existing approaches have computational complexities that are either linear (Hokamp and Liu, 2017) or exponential (Anderson et al., 2017) in the number of constraints. We present a algorithm for lexically constrained decoding with a complexity of O(1) in the number of constraints. We demonstrate the algorithms remarkable ability to properly place these constraints, and use it to explore the shaky relationship between model and BLEU scores. Our implementation is available as part of Sockeye.

Key facts. Cited by 181 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 34; 2023: 40; 2024: 28; 2025: 22; 2026: 26.

181 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  3. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 186
  4. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  5. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 162
  6. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  7. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  8. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  9. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  10. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  11. 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
  12. 2023Tractable Control for Autoregressive Language Generationcited by 65
38 more
  1. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64
  2. 2023Adaptive Machine Translation with Large Language Modelscited by 58
  3. 2021A Plug-and-Play Method for Controlled Text Generationcited by 55
  4. 2024Grammar-Aligned Decodingcited by 54
  5. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 52
  6. 2023Gotta be SAFE: A New Framework for Molecular Designcited by 45
  7. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  8. 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
  9. 2024Constrained Decoding for Secure Code Generationcited by 35
  10. 2021Guided Generation of Cause and Effectcited by 33
  11. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  12. 2023Escaping the sentence-level paradigm in machine translationcited by 27
  13. 2023Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learningcited by 26
  14. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  15. 2023Mixture of Soft Prompts for Controllable Data Generationcited by 23
  16. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  17. 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
  18. 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraintscited by 21
  19. 2021Facilitating Terminology Translation with Target Lemma Annotationscited by 19
  20. 2022Why is constrained neural language generation particularly challenging?cited by 19
  21. 2024DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inferencecited by 19
  22. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  23. 2023Domain Terminology Integration into Machine Translation: Leveraging Large Language Modelscited by 17
  24. 2023Chain-of-Dictionary Prompting Elicits Translation in Large Language Modelscited by 16
  25. 2021On the Evaluation of Machine Translation for Terminology Consistencycited by 15
  26. 2023Formally Specifying the High-Level Behavior of LLM-Based Agentscited by 15
  27. 2023Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decodingcited by 14
  28. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  29. 2025Constrained Sampling for Language Models Should Be Easy: An MCMC Perspectivecited by 14
  30. 2022Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQAcited by 13
  31. 2025Self-Steering Language Modelscited by 13
  32. 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correctioncited by 12
  33. 2022Automatic Song Translation for Tonal Languagescited by 12
  34. 2024Distilling Text Style Transfer With Self-Explanation From LLMscited by 12
  35. 2021Continuous Learning in Neural Machine Translation using Bilingual Dictionariescited by 11
  36. 2023Songs Across Borders: Singable and Controllable Neural Lyric Translationcited by 11
  37. 2024LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexiconscited by 11
  38. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11

50 most cited of 181 All 181 (JSON)