mlsanityData to 14 Oct 2026

Toward Controlled Generation of Text

arXiv 1703.00955 ↗First posted 2 Mar 2017cs.LG cs.AI cs.CLcited by 272

Not on the map. Why?

Abstract (arXiv)

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders and holistic attribute discriminators for effective imposition of semantic structures. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns highly interpretable representations from even only word annotations, and produces realistic sentences with desired attributes. Quantitative evaluation validates the accuracy of sentence and attribute generation.

Key facts. Cited by 272 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 99; 2022: 74; 2023: 36; 2024: 27; 2025: 22; 2026: 14.

272 papers.

Sort:

By area:

  1. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  2. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  3. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  4. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  5. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  6. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  7. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 161
  8. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  9. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 154
  10. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  11. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  12. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 129
38 more
  1. 2022Disentangled Representation Learningcited by 112
  2. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  4. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  5. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  6. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  7. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  8. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 70
  9. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 68
  10. 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
  11. 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classificationcited by 60
  12. 2021Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generationcited by 60
  13. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 58
  14. 2022LENS: A Learnable Evaluation Metric for Text Simplificationcited by 54
  15. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
  16. 2021Text Detoxification using Large Pre-trained Neural Modelscited by 52
  17. 2022Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Modelscited by 49
  18. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  19. 2022A Causal Lens for Controllable Text Generationcited by 45
  20. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  21. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  22. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 43
  23. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  24. 2024Large Language Models for Medicine: A Surveycited by 38
  25. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  26. 2021Efficient (Soft) Q-Learning for Text Generation with Limited Good Datacited by 37
  27. 2021Controllable Neural Dialogue Summarization with Personal Named Entity Planningcited by 36
  28. 2022Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learningcited by 36
  29. 2022Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Expertscited by 36
  30. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  31. 2022Intention-Conditioned Long-Term Human Egocentric Action Forecastingcited by 35
  32. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  33. 2022A Distributional Lens for Multi-Aspect Controllable Text Generationcited by 33
  34. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  35. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  36. 2021Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generationcited by 30
  37. 2022PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generationcited by 30
  38. 2022CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generationcited by 29

50 most cited of 272 All 272 (JSON)