# Long Text Generation via Adversarial Training with Leaked Information

arXiv: https://arxiv.org/abs/1709.08624 · HTML: https://mlsanity.com/paper/1709.08624/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2017.

## Built on by (most cited first, 30 of 100)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Step-unrolled Denoising Autoencoders for Text Generation](https://mlsanity.com/paper/2112.06749/) (2021)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Holo-Dex: Teaching Dexterity with Immersive Mixed Reality](https://mlsanity.com/paper/2210.06463/) (2022)
- [A Dense Reward View on Aligning Text-to-Image Diffusion with Preference](https://mlsanity.com/paper/2402.08265/) (2024)
- [Controllable Text Generation with Neurally-Decomposed Oracle](https://mlsanity.com/paper/2205.14219/) (2022)
- [Efficient (Soft) Q-Learning for Text Generation with Limited Good Data](https://mlsanity.com/paper/2106.07704/) (2021)
- [ValueNet: A New Dataset for Human Value Driven Dialogue System](https://mlsanity.com/paper/2112.06346/) (2021)
- [Survey on reinforcement learning for language processing](https://mlsanity.com/paper/2104.05565/) (2021)
- [Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models](https://mlsanity.com/paper/2203.01104/) (2022)
- [Preference-grounded Token-level Guidance for Language Model Fine-tuning](https://mlsanity.com/paper/2306.00398/) (2023)
- [Reward Gaming in Conditional Text Generation](https://mlsanity.com/paper/2211.08714/) (2022)
- [Assessing Judging Bias in Large Reasoning Models: An Empirical Study](https://mlsanity.com/paper/2504.09946/) (2025)
- [Tailoring Language Generation Models under Total Variation Distance](https://mlsanity.com/paper/2302.13344/) (2023)
- [Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning](https://mlsanity.com/paper/2405.15624/) (2024)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [Creativity and Machine Learning: A Survey](https://mlsanity.com/paper/2104.02726/) (2021)
- [Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks](https://mlsanity.com/paper/2301.03220/) (2023)
- [Diffusion-based Document Layout Generation](https://mlsanity.com/paper/2303.10787/) (2023)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs](https://mlsanity.com/paper/2409.01281/) (2024)
- [The King is Naked: on the Notion of Robustness for Natural Language Processing](https://mlsanity.com/paper/2112.07605/) (2021)
- [A survey on text generation using generative adversarial networks](https://mlsanity.com/paper/2212.11119/) (2022)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [TextBox: A Unified, Modularized, and Extensible Framework for Text Generation](https://mlsanity.com/paper/2101.02046/) (2021)
- [ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents](https://mlsanity.com/paper/2411.00927/) (2024)
- [On the Fairness of Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2103.00950/) (2021)
- [The Image Local Autoregressive Transformer](https://mlsanity.com/paper/2106.02514/) (2021)

## Abstract (arXiv)

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that use a discriminative model to guide the training of the generative model as a reinforcement learning policy has shown promising results in text generation. However, the scalar guiding signal is only available after the entire text has been generated and lacks intermediate information about text structure during the generative process. As such, it limits its success when the length of the generated text samples is long (more than 20 words). In this paper, we propose a new framework, called LeakGAN, to address the problem for long text generation. We allow the discriminative net to leak its own high-level extracted features to the generative net to further help the guidance. The generator incorporates such informative signals into all generation steps through an additional Manager module, which takes the extracted features of current generated words and outputs a latent vector to guide the Worker module for next-word generation. Our extensive experiments on synthetic data and various real-world tasks with Turing test demonstrate that LeakGAN is highly effective in long text generation and also improves the performance in short text generation scenarios. More importantly, without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between Manager and Worker.