mlsanityData to 7 Oct 2026

FUDGE: Controlled Text Generation With Future Discriminators

arXiv 2104.05218 ↗First posted 12 Apr 2021cs.CL cs.LGcited by 374

Not on the map. Why?

Cited by 48 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a pre-existing model G for generating text from a distribution of interest, FUDGE enables conditioning on a desired attribute a (for example, formality) while requiring access only to G's output logits. FUDGE learns an attribute predictor operating on a partial sequence, and uses this predictor's outputs to adjust G's original probabilities. We show that FUDGE models terms corresponding to a Bayesian decomposition of the conditional distribution of G given attribute a. Moreover, FUDGE can easily compose predictors for multiple desired attributes. We evaluate FUDGE on three tasks -- couplet completion in poetry, topic control in language generation, and formality change in machine translation -- and observe gains in all three tasks.

Key facts. Cited by 374 papers in the map (data through 7 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

38 of 54 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  8. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  9. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  10. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  11. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  12. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
26 more
  1. 2018Neural Network Acceptability Judgmentscited by 952
  2. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  3. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  4. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  5. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  6. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  7. 2017Toward Controlled Generation of Textcited by 271
  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. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  11. 2018Bottom-Up Abstractive Summarizationcited by 177
  12. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 147
  13. 2019What makes a good conversation? How controllable attributes affect human judgmentscited by 140
  14. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  15. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  16. 2018Learning to Write with Cooperative Discriminatorscited by 119
  17. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  18. 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 78
  19. 2020Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learningcited by 65
  20. 2020Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generationcited by 47
  21. 2018Pragmatically Informative Image Captioning with Character-Level Inferencecited by 42
  22. 2018Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhymecited by 35
  23. 2019Pragmatically Informative Text Generationcited by 32
  24. 2019Fluent Translations from Disfluent Speech in End-to-End Speech Translationcited by 22
  25. 2019Can Unconditional Language Models Recover Arbitrary Sentences?cited by 15
  26. 2016Chinese Song Iambics Generation with Neural Attention-based Modelcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 48; 2023: 83; 2024: 95; 2025: 70; 2026: 70.

374 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  3. 2023Steering Language Models With Activation Engineeringcited by 824
  4. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 454
  5. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  6. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  7. 2023Challenges and Applications of Large Language Modelscited by 251
  8. 2024From r to Q^*: Your Language Model is Secretly a Q-Functioncited by 242
  9. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  10. 2022Multi-Game Decision Transformerscited by 212
  11. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  12. 2023Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hackingcited by 195
38 more
  1. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  2. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  3. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  4. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
  5. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 181
  6. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 162
  7. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  8. 2023Protein Design with Guided Discrete Diffusioncited by 154
  9. 2024Simple Guidance Mechanisms for Discrete Diffusion Modelscited by 148
  10. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 140
  11. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 137
  12. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  13. 2023Controlled Decoding from Language Modelscited by 133
  14. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  15. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 127
  16. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Modelscited by 124
  17. 2024BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Samplingcited by 120
  18. 2024Theoretical guarantees on the best-of-n alignment policycited by 116
  19. 2024A Thorough Examination of Decoding Methods in the Era of LLMscited by 112
  20. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  21. 2024Aligner: Efficient Alignment by Learning to Correctcited by 96
  22. 2023Amortizing intractable inference in large language modelscited by 94
  23. 2023Stay on topic with Classifier-Free Guidancecited by 90
  24. 2024Tuning Language Models by Proxycited by 88
  25. 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlocited by 85
  26. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 82
  27. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  28. 2023Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelcited by 79
  29. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  30. 2022RankGen: Improving Text Generation with Large Ranking Modelscited by 72
  31. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  32. 2023Contrastive Decoding Improves Reasoning in Large Language Modelscited by 71
  33. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  34. 2023Word Embeddings Are Steers for Language Modelscited by 70
  35. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  36. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 66
  37. 2023Tractable Control for Autoregressive Language Generationcited by 65
  38. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64

50 most cited of 374 All 374 (JSON)