mlsanityData to 7 Oct 2026

Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents

arXiv 2202.05971 ↗First posted 12 Feb 2022cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However, when it comes to the contextual coherence of the generated responses, there is still room for improvement. Hence, to improve the contextual coherence, we propose a novel Uncertainty Aware CVAE (UA-CVAE) framework. The UA-CVAE framework involves approximating and incorporating the aleatoric uncertainty during response generation. We apply our framework to both personalized and empathetic dialogue generation. Empirical results show that our framework significantly improves the contextual coherence of the generated response. Additionally, we introduce a novel automatic metric for measuring contextual coherence, which was found to correlate positively with human judgement.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 12 Feb 2022.

Builds on

17 of 24 references.

References · 17

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  5. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  6. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  7. 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
  8. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  9. 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
  10. 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
  11. 2019Exploiting Persona Information for Diverse Generation of Conversational Responsescited by 58
  12. 2019Guiding Variational Response Generator to Exploit Personacited by 25
5 more
  1. 2018A Hierarchical Latent Structure for Variational Conversation Modelingcited by 17
  2. 2019EmpDG: Multiresolution Interactive Empathetic Dialogue Generationcited by 14
  3. 2021Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generationcited by 9
  4. 2021Generating Personalized Dialogue via Multi-Task Meta-Learningcited by 8
  5. 2021DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 5; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 19
  2. 2025PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialoguescited by 16
  3. 2024Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactionscited by 13
  4. 2023Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledgecited by 12
  5. 2024PersoBench: Benchmarking Personalized Response Generation in Large Language Modelscited by 12
  6. 2025SYNTHEMPATHY: A Scalable Empathy Corpus Generated Using LLMs Without Any Crowdsourcingcited by 7
  7. 2023An Empirical Bayes Framework for Open-Domain Dialogue Generationcited by 5
  8. 2025Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generationcited by 3
  9. 2025Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomycited by 3
  10. 2025Modeling the One-to-Many Property in Open-Domain Dialogue with LLMscited by 3
  11. 2023Artificial Empathy Classification: A Survey of Deep Learning Techniques, Datasets, and Evaluation Scalescited by 2
  12. 2023Partially Randomizing Transformer Weights for Dialogue Response Diversitycited by 1
2 more
  1. 2026Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generationcited by 0
  2. 2026PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluationcited by 0