mlsanityData to 14 Oct 2026

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

arXiv 1811.10996 ↗First posted 14 Nov 2018cs.CL cs.AI cs.LGcited by 94

Not on the map. Why?

Abstract (arXiv)

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs while maintaining generation quality, since RNNs generate sentences sequentially (or with beam search) from the first word to the last. In this paper, we propose CGMH, a novel approach using Metropolis-Hastings sampling for constrained sentence generation. CGMH allows complicated constraints such as the occurrence of multiple keywords in the target sentences, which cannot be handled in traditional RNN-based approaches. Moreover, CGMH works in the inference stage, and does not require parallel corpora for training. We evaluate our method on a variety of tasks, including keywords-to-sentence generation, unsupervised sentence paraphrasing, and unsupervised sentence error correction. CGMH achieves high performance compared with previous supervised methods for sentence generation. Our code is released at https://github.com/NingMiao/CGMH

Key facts. Cited by 94 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 19; 2023: 14; 2024: 10; 2025: 13; 2026: 10.

94 papers.

Sort:

By area:

  1. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
  2. 2022Generating Sequences by Learning to Self-Correctcited by 277
  3. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 161
  4. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 154
  5. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  6. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  7. 2023Aligning Language Models with Preferences through f-divergence Minimizationcited by 120
  8. 2023Amortizing intractable inference in large language modelscited by 97
  9. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  10. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 80
  11. 2021A Plug-and-Play Method for Controlled Text Generationcited by 56
  12. 2025Edit Flows: Flow Matching with Edit Operationscited by 55
38 more
  1. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 46
  2. 2024Space Group Informed Transformer for Crystalline Materials Generationcited by 41
  3. 2021Coherence boosting: When your pretrained language model is not paying enough attentioncited by 38
  4. 2024Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Modelscited by 35
  5. 2023Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasingcited by 31
  6. 2022Learning to Model Editing Processescited by 30
  7. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  8. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  9. 2025Sample, Don't Search: Rethinking Test-Time Alignment for Language Modelscited by 22
  10. 2022Why is constrained neural language generation particularly challenging?cited by 19
  11. 2021Controllable Summarization with Constrained Markov Decision Processcited by 17
  12. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  13. 2025Constrained Discrete Diffusioncited by 17
  14. 2023Prompt-Based Editing for Text Style Transfercited by 16
  15. 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translationcited by 16
  16. 2021NAREOR: The Narrative Reordering Problemcited by 14
  17. 2023Zero-shot Clarifying Question Generation for Conversational Searchcited by 14
  18. 2021ConRPG: Paraphrase Generation using Contexts as Regularizercited by 13
  19. 2022A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarizationcited by 13
  20. 2023Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decodingcited by 13
  21. 2023PathFinder: Guided Search over Multi-Step Reasoning Pathscited by 12
  22. 2025Flexible-length Text Infilling for Discrete Diffusion Modelscited by 12
  23. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  24. 2022Quantum Natural Language Generation on Near-Term Devicescited by 11
  25. 2021Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learningcited by 10
  26. 2021Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNetcited by 10
  27. 2021Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Modelscited by 9
  28. 2022Converge to the Truth: Factual Error Correction via Iterative Constrained Editingcited by 9
  29. 2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMscited by 9
  30. 2021SAPPHIRE: Approaches for Enhanced Concept-to-Text Generationcited by 8
  31. 2021Unsupervised Editing for Counterfactual Storiescited by 8
  32. 2024Constrained Decoding for Cross-lingual Label Projectioncited by 8
  33. 2021Language Model Augmented Relevance Scorecited by 7
  34. 2025Neuro-Symbolic Predictive Process Monitoringcited by 7
  35. 2021Controlling Text Edition by Changing Answers of Specific Questionscited by 6
  36. 2022UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendationcited by 6
  37. 2022AutoTemplate: A Simple Recipe for Lexically Constrained Text Generationcited by 6
  38. 2021Triangular Bidword Generation for Sponsored Search Auctioncited by 5

50 most cited of 94 All 94 (JSON)