mlsanityData to 14 Oct 2026

Learning to Write with Cooperative Discriminators

arXiv 1805.06087 ↗First posted 16 May 2018cs.CLcited by 119

Not on the map. Why?

Abstract (arXiv)

Recurrent Neural Networks (RNNs) are powerful autoregressive sequence models, but when used to generate natural language their output tends to be overly generic, repetitive, and self-contradictory. We postulate that the objective function optimized by RNN language models, which amounts to the overall perplexity of a text, is not expressive enough to capture the notion of communicative goals described by linguistic principles such as Grice's Maxims. We propose learning a mixture of multiple discriminative models that can be used to complement the RNN generator and guide the decoding process. Human evaluation demonstrates that text generated by our system is preferred over that of baselines by a large margin and significantly enhances the overall coherence, style, and information content of the generated text.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 27; 2023: 26; 2024: 21; 2025: 9; 2026: 4.

119 papers.

Sort:

By area:

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  3. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  4. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  5. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 422
  6. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  7. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 246
  8. 2024Chain-of-Thought Reasoning Without Promptingcited by 210
  9. 2021Generating Datasets with Pretrained Language Modelscited by 193
  10. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 138
  11. 2024BetterV: Controlled Verilog Generation with Discriminative Guidancecited by 100
  12. 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 97
38 more
  1. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 94
  2. 2021Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Textcited by 89
  3. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  4. 2023Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelcited by 79
  5. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  6. 2022RankGen: Improving Text Generation with Large Ranking Modelscited by 72
  7. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  8. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 70
  9. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 67
  10. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  11. 2021A Plug-and-Play Method for Controlled Text Generationcited by 56
  12. 2021MERMAID: Metaphor Generation with Symbolism and Discriminative Decodingcited by 49
  13. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  14. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  15. 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
  16. 2023Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversationscited by 38
  17. 2023GRACE: Discriminator-Guided Chain-of-Thought Reasoningcited by 35
  18. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 35
  19. 2024Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talkcited by 34
  20. 2021PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decodingcited by 33
  21. 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
  22. 2022A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generationcited by 28
  23. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelscited by 27
  24. 2021Parallel Refinements for Lexically Constrained Text Generation with BARTcited by 24
  25. 2024Non-Exchangeable Conformal Language Generation with Nearest Neighborscited by 21
  26. 2023Human-in-the-Loop through Chain-of-Thoughtcited by 20
  27. 2022Why is constrained neural language generation particularly challenging?cited by 19
  28. 2023Stealing the Decoding Algorithms of Language Modelscited by 19
  29. 2023Adaptive and Personalized Exercise Generation for Online Language Learningcited by 19
  30. 2024DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inferencecited by 19
  31. 2022Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMCcited by 17
  32. 2022A Mixture-of-Expert Approach to RL-based Dialogue Managementcited by 16
  33. 2025Advancing LLM Safe Alignment with Safety Representation Rankingcited by 16
  34. 2023Controlling Pre-trained Language Models for Grade-Specific Text Simplificationcited by 14
  35. 2021Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generationcited by 13
  36. 2024Measuring memorization in RLHF for code completioncited by 13
  37. 2021On-the-Fly Attention Modulation for Neural Generationcited by 12
  38. 2022Knowledge Infused Decodingcited by 12

50 most cited of 119 All 119 (JSON)