# Implicit Deep Latent Variable Models for Text Generation

arXiv: https://arxiv.org/abs/1908.11527 · HTML: https://mlsanity.com/paper/1908.11527/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 26 of 26)

- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [Latent Diffusion Energy-Based Model for Interpretable Text Modeling](https://mlsanity.com/paper/2206.05895/) (2022)
- [Consistency Regularization for Variational Auto-Encoders](https://mlsanity.com/paper/2105.14859/) (2021)
- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation](https://mlsanity.com/paper/2204.13031/) (2022)
- [ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation](https://mlsanity.com/paper/2104.08006/) (2021)
- [Semantic Representation for Dialogue Modeling](https://mlsanity.com/paper/2105.10188/) (2021)
- [Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders](https://mlsanity.com/paper/2109.07169/) (2021)
- [A Survey to Recent Progress Towards Understanding In-Context Learning](https://mlsanity.com/paper/2402.02212/) (2024)
- [AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling](https://mlsanity.com/paper/2205.05862/) (2022)
- [GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents](https://mlsanity.com/paper/2412.10410/) (2024)
- [Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events](https://mlsanity.com/paper/2101.00822/) (2021)
- [Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness](https://mlsanity.com/paper/2110.12381/) (2021)
- [DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space](https://mlsanity.com/paper/2404.06760/) (2024)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable](https://mlsanity.com/paper/2210.12640/) (2022)
- [On the Latent Holes of VAEs for Text Generation](https://mlsanity.com/paper/2110.03318/) (2021)
- [Hidden Schema Networks](https://mlsanity.com/paper/2207.03777/) (2022)
- [PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation](https://mlsanity.com/paper/2210.03496/) (2022)
- [Improving Variational Autoencoders with Density Gap-based Regularization](https://mlsanity.com/paper/2211.00321/) (2022)
- [VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder](https://mlsanity.com/paper/2307.00852/) (2023)
- [An Overview on Controllable Text Generation via Variational Auto-Encoders](https://mlsanity.com/paper/2211.07954/) (2022)
- [Noun2Verb: Probabilistic frame semantics for word class conversion](https://mlsanity.com/paper/2205.06321/) (2022)
- [Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation](https://mlsanity.com/paper/2305.15025/) (2023)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)
- [Unlocking Latent Personalization in LLMs](https://mlsanity.com/paper/2609.33182/) (2026)

## Abstract (arXiv)

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption is often made on the variational posteriors; and meanwhile (2) a notorious "posterior collapse" issue occurs. In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared with Gaussian-based posteriors. We further develop an LVM to directly match the aggregated posterior to the prior. It can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue. We demonstrate the effectiveness and versatility of our models in various text generation scenarios, including language modeling, unaligned style transfer, and dialog response generation. The source code to reproduce our experimental results is available on GitHub.