# Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

arXiv: https://arxiv.org/abs/1908.06605 · HTML: https://mlsanity.com/paper/1908.06605/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 30 of 62)

- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation](https://mlsanity.com/paper/2107.02137/) (2021)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation](https://mlsanity.com/paper/2307.15337/) (2023)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models](https://mlsanity.com/paper/2310.10049/) (2023)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [CPM-2: Large-scale Cost-effective Pre-trained Language Models](https://mlsanity.com/paper/2106.10715/) (2021)
- [Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence](https://mlsanity.com/paper/2105.08963/) (2021)
- [HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models](https://mlsanity.com/paper/2409.16191/) (2024)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [A Review of Deep Learning for Video Captioning](https://mlsanity.com/paper/2304.11431/) (2023)
- [Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2212.04634/) (2022)
- [Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation](https://mlsanity.com/paper/2105.14778/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Data-to-text Generation with Variational Sequential Planning](https://mlsanity.com/paper/2202.13756/) (2022)
- [EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention](https://mlsanity.com/paper/2210.12463/) (2022)
- [What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation](https://mlsanity.com/paper/2408.14622/) (2024)
- [CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark](https://mlsanity.com/paper/2112.13610/) (2021)
- [A Corpus for Understanding and Generating Moral Stories](https://mlsanity.com/paper/2204.09438/) (2022)
- [DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer](https://mlsanity.com/paper/2110.05999/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [MOVER: Mask, Over-generate and Rank for Hyperbole Generation](https://mlsanity.com/paper/2109.07726/) (2021)
- [CLEVA: Chinese Language Models EVAluation Platform](https://mlsanity.com/paper/2308.04813/) (2023)
- [HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models](https://mlsanity.com/paper/2110.04400/) (2021)
- [Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain](https://mlsanity.com/paper/2305.03256/) (2023)

## Abstract (arXiv)

Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions. To address these issues, we propose a Planning-based Hierarchical Variational Model (PHVM). Our model first plans a sequence of groups (each group is a subset of input items to be covered by a sentence) and then realizes each sentence conditioned on the planning result and the previously generated context, thereby decomposing long text generation into dependent sentence generation sub-tasks. To capture expression diversity, we devise a hierarchical latent structure where a global planning latent variable models the diversity of reasonable planning and a sequence of local latent variables controls sentence realization. Experiments show that our model outperforms state-of-the-art baselines in long and diverse text generation.