mlsanityData to 14 Oct 2026

An Empirical Bayes Framework for Open-Domain Dialogue Generation

arXiv 2311.10945 ↗First posted 18 Nov 2023cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

To engage human users in meaningful conversation, open-domain dialogue agents are required to generate diverse and contextually coherent dialogue. Despite recent advancements, which can be attributed to the usage of pretrained language models, the generation of diverse and coherent dialogue remains an open research problem. A popular approach to address this issue involves the adaptation of variational frameworks. However, while these approaches successfully improve diversity, they tend to compromise on contextual coherence. Hence, we propose the Bayesian Open-domain Dialogue with Empirical Bayes (BODEB) framework, an empirical bayes framework for constructing an Bayesian open-domain dialogue agent by leveraging pretrained parameters to inform the prior and posterior parameter distributions. Empirical results show that BODEB achieves better results in terms of both diversity and coherence compared to variational frameworks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 18 Nov 2023.

Builds on

30 of 54 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  8. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  9. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  10. 2015Weight Uncertainty in Neural Networkscited by 554
  11. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  12. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
18 more
  1. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 343
  2. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  3. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 209
  4. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  5. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  6. 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
  7. 2018The promises and pitfalls of Stochastic Gradient Langevin Dynamicscited by 56
  8. 2020How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Contextcited by 53
  9. 2020Variational Transformers for Diverse Response Generationcited by 36
  10. 2019Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayescited by 32
  11. 2019Guiding Variational Response Generator to Exploit Personacited by 25
  12. 2021Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoderscited by 18
  13. 2019A Discrete CVAE for Response Generation on Short-Text Conversationcited by 17
  14. 2017A Conditional Variational Framework for Dialog Generationcited by 16
  15. 2022Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agentscited by 14
  16. 2021Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generationcited by 9
  17. 2022Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representationcited by 4
  18. 2016Empirical Bayes Methods for Prior Estimation in Systems Medicinecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2026EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimizationcited by 5
  2. 2024Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuningcited by 4
  3. 2025Modeling the One-to-Many Property in Open-Domain Dialogue with LLMscited by 3
  4. 2025DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systemscited by 0
  5. 2026Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generationcited by 0