mlsanityData to 7 Oct 2026

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

arXiv 1809.05972 ↗First posted 16 Sep 2018cs.CL cs.AIcited by 114

Not on the map. Why?

Abstract (arXiv)

Responses generated by neural conversational models tend to lack informativeness and diversity. We present Adversarial Information Maximization (AIM), an adversarial learning strategy that addresses these two related but distinct problems. To foster response diversity, we leverage adversarial training that allows distributional matching of synthetic and real responses. To improve informativeness, our framework explicitly optimizes a variational lower bound on pairwise mutual information between query and response. Empirical results from automatic and human evaluations demonstrate that our methods significantly boost informativeness and diversity.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 38; 2022: 24; 2023: 18; 2024: 18; 2025: 11; 2026: 4.

114 papers.

Sort:

By area:

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2022Red Teaming Language Models with Language Modelscited by 983
  3. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  4. 2023MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problemscited by 128
  5. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 97
  6. 2022On Decoding Strategies for Neural Text Generatorscited by 89
  7. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 77
  8. 2024Catastrophic Failure of LLM Unlearning via Quantizationcited by 76
  9. 2020Dialogue Response Ranking Training with Large-Scale Human Feedback Datacited by 68
  10. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  11. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 56
  12. 2024A Closer Look at Machine Unlearning for Large Language Modelscited by 54
38 more
  1. 2022On the Blind Spots of Model-Based Evaluation Metrics for Text Generationcited by 48
  2. 2024k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Textcited by 46
  3. 2024Learning to Edit: Aligning LLMs with Knowledge Editingcited by 43
  4. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  5. 2021Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterancescited by 40
  6. 2021Coherence boosting: When your pretrained language model is not paying enough attentioncited by 38
  7. 2021MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understandingcited by 36
  8. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  9. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  10. 2021MMChat: Multi-Modal Chat Dataset on Social Mediacited by 30
  11. 2024Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancementcited by 30
  12. 2022Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russiancited by 29
  13. 2022Semantic Diversity in Dialogue with Natural Language Inferencecited by 28
  14. 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26
  15. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
  16. 2022A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generationcited by 25
  17. 2021Decomposed Mutual Information Estimation for Contrastive Representation Learningcited by 24
  18. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
  19. 2021RetGen: A Joint framework for Retrieval and Grounded Text Generation Modelingcited by 22
  20. 2022Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Expertscited by 19
  21. 2022Why is constrained neural language generation particularly challenging?cited by 19
  22. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 19
  23. 2021Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoderscited by 18
  24. 2023Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularizationcited by 17
  25. 2024Evaluating Diversity in Automatic Poetry Generationcited by 17
  26. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  27. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  28. 2023Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregationcited by 16
  29. 2021Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimizationcited by 15
  30. 2023Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generationcited by 14
  31. 2021Controllable and Diverse Text Generation in E-commercecited by 13
  32. 2021Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Trainingcited by 13
  33. 2022MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languagescited by 13
  34. 2023MidMed: Towards Mixed-Type Dialogues for Medical Consultationcited by 13
  35. 2024Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Taskscited by 13
  36. 2025SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Modelscited by 13
  37. 2021Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNetcited by 10
  38. 2023Lightweight reranking for language model generationscited by 10

50 most cited of 114 All 114 (JSON)