mlsanityData to 7 Oct 2026

Controllable Text Generation with Neurally-Decomposed Oracle

arXiv 2205.14219 ↗First posted 27 May 2022cs.CLcited by 41

Not on the map. Why?

Abstract (arXiv)

We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO). Given a pre-trained base language model and a sequence-level boolean oracle function, we propose to decompose the oracle function into token-level guidance to steer the base model in text generation. Specifically, the token-level guidance is approximated by a neural model trained with examples sampled from the base model, demanding no additional auxiliary labeled data. Based on posterior regularization, we present the closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation. We further provide a theoretical analysis of how the approximation quality of NADO affects the controllable generation results. Experiments conducted on two applications: (1) text generation with lexical constraints and (2) machine translation with formality control demonstrate that our framework efficiently guides the base model towards the given oracle while maintaining high generation quality.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

43 of 66 references.

References · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  8. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  9. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  10. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  11. 2019Defending Against Neural Fake Newscited by 553
  12. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
31 more
  1. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  2. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
  3. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  4. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  5. 2016Image Captioning with Semantic Attentioncited by 260
  6. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  7. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
  8. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  9. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  10. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  11. 2019Levenshtein Transformercited by 197
  12. 2015A Neural Conversational Modelcited by 195
  13. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  14. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  15. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  16. 2021Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologiescited by 128
  17. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  18. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  19. 2020A Distributional Approach to Controlled Text Generationcited by 117
  20. 2020Towards Controllable Biases in Language Generationcited by 112
  21. 2016Guided Open Vocabulary Image Captioning with Constrained Beam Searchcited by 105
  22. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  23. 2020Content Planning for Neural Story Generation with Aristotelian Rescoringcited by 92
  24. 2020Lexically Constrained Neural Machine Translation with Levenshtein Transformercited by 45
  25. 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
  26. 2022Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Featurescited by 24
  27. 2019Fluent Translations from Disfluent Speech in End-to-End Speech Translationcited by 22
  28. 2021Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codescited by 19
  29. 2022Go Back in Time: Generating Flashbacks in Stories with Event Temporal Promptscited by 15
  30. 2021InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Modelcited by 14
  31. 2020POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-trainingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 16; 2024: 13; 2025: 6; 2026: 4.

41 papers.

Sort:

By area:

  1. 2023Controlled Decoding from Language Modelscited by 133
  2. 2023Amortizing intractable inference in large language modelscited by 94
  3. 2023Stay on topic with Classifier-Free Guidancecited by 90
  4. 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
  5. 2023Tractable Control for Autoregressive Language Generationcited by 65
  6. 2023Controlled Text Generation via Language Model Arithmeticcited by 51
  7. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  8. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 43
  9. 2024DeepEdit: Knowledge Editing as Decoding with Constraintscited by 33
  10. 2024Offset Unlearning for Large Language Modelscited by 33
  11. 2024Adaptable Logical Control for Large Language Modelscited by 30
  12. 2022Controllable Text Generation via Probability Density Estimation in the Latent Spacecited by 27
29 more
  1. 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraintscited by 21
  2. 2025Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Samplingcited by 20
  3. 2023Formally Specifying the High-Level Behavior of LLM-Based Agentscited by 15
  4. 2023Next Steps for Human-Centered Generative AI: A Technical Perspectivecited by 13
  5. 2024Controllable Generation via Locally Constrained Resamplingcited by 11
  6. 2024RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Frameworkcited by 11
  7. 2024Monotonic Paraphrasing Improves Generalization of Language Model Promptingcited by 10
  8. 2025TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generationcited by 8
  9. 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposalscited by 8
  10. 2023Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyondcited by 7
  11. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  12. 2024Controllable Text Generation in the Instruction-Tuning Eracited by 7
  13. 2024Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxificationcited by 7
  14. 2024Guaranteed Generation from Large Language Modelscited by 7
  15. 2023Sequentially Controlled Text Generationcited by 5
  16. 2024Control Large Language Models via Divide and Conquercited by 5
  17. 2024Familiarity-Aware Evidence Compression for Retrieval-Augmented Generationcited by 4
  18. 2024On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directionscited by 3
  19. 2025ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Searchcited by 3
  20. 2026Steering Language Models Before They Speak: Logit-Level Interventionscited by 3
  21. 2023Controlled Text Generation for Black-box Language Models via Score-based Progressive Editorcited by 2
  22. 2023DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Modelscited by 1
  23. 2023BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generationcited by 1
  24. 2024Towards Minimal Targeted Updates of Language Models with Targeted Negative Trainingcited by 1
  25. 2025DiscoSum: Discourse-aware News Summarizationcited by 0
  26. 2025Black-Box Guardrail Reverse-engineering Attackcited by 0
  27. 2025Learning Tractable Distributions Of Language Model Continuationscited by 0
  28. 2026Margin-calibrated Classifier Guidance for Property-driven Synthesis Planningcited by 0
  29. 2026The Parser Already Knows: Lightweight Bias Correction in Constrained Decodingcited by 0