mlsanityData to 7 Oct 2026

Adversarial Learning for Neural Dialogue Generation

arXiv 1701.06547 ↗First posted 23 Jan 2017cs.CLcited by 103

Not on the map. Why?

Abstract (arXiv)

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning (RL) problem where we jointly train two systems, a generative model to produce response sequences, and a discriminator---analagous to the human evaluator in the Turing test--- to distinguish between the human-generated dialogues and the machine-generated ones. The outputs from the discriminator are then used as rewards for the generative model, pushing the system to generate dialogues that mostly resemble human dialogues. In addition to adversarial training we describe a model for adversarial em evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 2; 2021: 38; 2022: 24; 2023: 19; 2024: 6; 2025: 6; 2026: 5.

103 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 283
  3. 2023User Behavior Simulation with Large Language Model based Agentscited by 136
  4. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  5. 2020Human-centric Dialog Training via Offline Reinforcement Learningcited by 92
  6. 2020Text Generation by Learning from Demonstrationscited by 64
  7. 2022MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversationcited by 56
  8. 2018Multi-Agent Imitation Learning for Driving Simulationcited by 49
  9. 2022Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal Viewcited by 31
  10. 2021Defending Against Backdoor Attacks in Natural Language Generationcited by 30
  11. 2021OTTers: One-turn Topic Transitions for Open-Domain Dialoguecited by 29
  12. 2022A Literature Survey of Recent Advances in Chatbotscited by 26
38 more
  1. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  2. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 21
  3. 2022Why is constrained neural language generation particularly challenging?cited by 19
  4. 2024ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generatorcited by 19
  5. 2021Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoderscited by 18
  6. 2021Speaker Turn Modeling for Dialogue Act Classificationcited by 18
  7. 2022Toward Human-Like Evaluation for Natural Language Generation with Error Analysiscited by 18
  8. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  9. 2021OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contextscited by 16
  10. 2022A Mixture-of-Expert Approach to RL-based Dialogue Managementcited by 16
  11. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  12. 2021Time-Series Regeneration with Convolutional Recurrent Generative Adversarial Network for Remaining Useful Life Estimationcited by 15
  13. 2022Row Conditional-TGAN for generating synthetic relational databasescited by 15
  14. 2025Adaptive Social Learning via Mode Policy Optimization for Language Agentscited by 15
  15. 2021InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Modelcited by 14
  16. 2021Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbotscited by 14
  17. 2021To Beam Or Not To Beam: That is a Question of Cooperation for Language GANscited by 14
  18. 2021Controllable and Diverse Text Generation in E-commercecited by 13
  19. 2021Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Trainingcited by 13
  20. 2021Sentence Similarity Based on Contextscited by 12
  21. 2022An Equal-Size Hard EM Algorithm for Diverse Dialogue Generationcited by 11
  22. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  23. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  24. 2023Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challengescited by 10
  25. 2026ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenderscited by 10
  26. 2021Partition-Guided GANscited by 9
  27. 2021Modulating Language Models with Emotionscited by 9
  28. 2021Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generationcited by 8
  29. 2022Dynamic Planning in Open-Ended Dialogue using Reinforcement Learningcited by 8
  30. 2023Graph Contrastive Learning with Generative Adversarial Networkcited by 8
  31. 2022The Dialog Must Go On: Improving Visual Dialog via Generative Self-Trainingcited by 7
  32. 2023Improved Training of Mixture-of-Experts Language GANscited by 7
  33. 2024Harnessing Business and Media Insights with Large Language Modelscited by 7
  34. 2021Towards Standard Criteria for human evaluation of Chatbots: A Surveycited by 6
  35. 2022Diversifying Neural Dialogue Generation via Negative Distillationcited by 6
  36. 2022PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanismcited by 6
  37. 2021Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillationcited by 5
  38. 2021Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Rewardcited by 5

50 most cited of 103 All 103 (JSON)