# Latent Variable Dialogue Models and their Diversity

arXiv: https://arxiv.org/abs/1702.05962 · HTML: https://mlsanity.com/paper/1702.05962/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 8 of 8)

- [Semantic Diversity in Dialogue with Natural Language Inference](https://mlsanity.com/paper/2205.01497/) (2022)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation](https://mlsanity.com/paper/2104.08857/) (2021)
- [Annotations Mitigate Post-Training Mode Collapse](https://mlsanity.com/paper/2605.09995/) (2026)
- [Prompting for a conversation: How to control a dialog model?](https://mlsanity.com/paper/2209.11068/) (2022)
- [Pragmatically Appropriate Diversity for Dialogue Evaluation](https://mlsanity.com/paper/2304.02812/) (2023)
- [Android Security using NLP Techniques: A Review](https://mlsanity.com/paper/2107.03072/) (2021)
- [Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://mlsanity.com/paper/2204.02710/) (2022)

## Abstract (arXiv)

We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the `boring output' issue of deterministic dialogue models. Experiments show that our model generates more diverse outputs than baseline models, and also generates more consistently acceptable output than sampling from a deterministic encoder-decoder model.