# Guiding Variational Response Generator to Exploit Persona

arXiv: https://arxiv.org/abs/1911.02390 · HTML: https://mlsanity.com/paper/1911.02390/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2019.

## Built on by (most cited first, 25 of 25)

- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge](https://mlsanity.com/paper/2112.08619/) (2021)
- [A Personalized Dialogue Generator with Implicit User Persona Detection](https://mlsanity.com/paper/2204.07372/) (2022)
- [Modeling Bilingual Conversational Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2107.11164/) (2021)
- [Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization](https://mlsanity.com/paper/2305.12782/) (2023)
- [Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling](https://mlsanity.com/paper/2112.13556/) (2021)
- [Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents](https://mlsanity.com/paper/2202.05971/) (2022)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Towards Making the Most of Dialogue Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2109.00668/) (2021)
- [Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description](https://mlsanity.com/paper/2111.15093/) (2021)
- [WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue](https://mlsanity.com/paper/2306.03361/) (2023)
- [Generating Personalized Dialogue via Multi-Task Meta-Learning](https://mlsanity.com/paper/2108.03377/) (2021)
- [Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation](https://mlsanity.com/paper/2205.13346/) (2022)
- [PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue](https://mlsanity.com/paper/2302.06674/) (2023)
- [TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System](https://mlsanity.com/paper/2109.05187/) (2021)
- [An Empirical Bayes Framework for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2311.10945/) (2023)
- [DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation](https://mlsanity.com/paper/2111.11363/) (2021)
- [Context-dependent Instruction Tuning for Dialogue Response Generation](https://mlsanity.com/paper/2311.07006/) (2023)
- [Towards End-to-End Open Conversational Machine Reading](https://mlsanity.com/paper/2210.07113/) (2022)
- [Rumor Detection on Social Media with Reinforcement Learning-based Key Propagation Graph Generator](https://mlsanity.com/paper/2405.13094/) (2024)
- [PGTask: Introducing the Task of Profile Generation from Dialogues](https://mlsanity.com/paper/2304.06634/) (2023)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics](https://mlsanity.com/paper/2507.15518/) (2025)
- [Transformer-Based Conditioned Variational Autoencoder for Dialogue Generation](https://mlsanity.com/paper/2210.12326/) (2022)

## Abstract (arXiv)

Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progresses achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via the End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results.