# Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents

arXiv: https://arxiv.org/abs/2202.05971 · HTML: https://mlsanity.com/paper/2202.05971/

## Key facts

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

## Builds on (most cited first, 17 of 17)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [You Impress Me: Dialogue Generation via Mutual Persona Perception](https://mlsanity.com/paper/2004.05388/) (2020)
- [MojiTalk: Generating Emotional Responses at Scale](https://mlsanity.com/paper/1711.04090/) (2017)
- [Exploiting Persona Information for Diverse Generation of Conversational Responses](https://mlsanity.com/paper/1905.12188/) (2019)
- [Guiding Variational Response Generator to Exploit Persona](https://mlsanity.com/paper/1911.02390/) (2019)
- [A Hierarchical Latent Structure for Variational Conversation Modeling](https://mlsanity.com/paper/1804.03424/) (2018)
- [EmpDG: Multiresolution Interactive Empathetic Dialogue Generation](https://mlsanity.com/paper/1911.08698/) (2019)
- [Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation](https://mlsanity.com/paper/2104.08857/) (2021)
- [Generating Personalized Dialogue via Multi-Task Meta-Learning](https://mlsanity.com/paper/2108.03377/) (2021)
- [DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation](https://mlsanity.com/paper/2111.11363/) (2021)

## Built on by (most cited first, 14 of 14)

- [Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations](https://mlsanity.com/paper/2405.17974/) (2024)
- [PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues](https://mlsanity.com/paper/2502.21017/) (2025)
- [Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions](https://mlsanity.com/paper/2405.16402/) (2024)
- [PersoBench: Benchmarking Personalized Response Generation in Large Language Models](https://mlsanity.com/paper/2410.03198/) (2024)
- [Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge](https://mlsanity.com/paper/2306.04657/) (2023)
- [SYNTHEMPATHY: A Scalable Empathy Corpus Generated Using LLMs Without Any Crowdsourcing](https://mlsanity.com/paper/2502.17857/) (2025)
- [An Empirical Bayes Framework for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2311.10945/) (2023)
- [Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation](https://mlsanity.com/paper/2502.11423/) (2025)
- [Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2505.21907/) (2025)
- [Modeling the One-to-Many Property in Open-Domain Dialogue with LLMs](https://mlsanity.com/paper/2506.15131/) (2025)
- [Artificial Empathy Classification: A Survey of Deep Learning Techniques, Datasets, and Evaluation Scales](https://mlsanity.com/paper/2310.00010/) (2023)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation](https://mlsanity.com/paper/2601.01037/) (2026)
- [PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation](https://mlsanity.com/paper/2602.04493/) (2026)

## 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.