# Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation

arXiv: https://arxiv.org/abs/2003.11530 · HTML: https://mlsanity.com/paper/2003.11530/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse](https://mlsanity.com/paper/2112.04660/) (2021)
- [Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction](https://mlsanity.com/paper/2205.01608/) (2022)
- [A survey on text generation using generative adversarial networks](https://mlsanity.com/paper/2212.11119/) (2022)
- [Time-series Generation by Contrastive Imitation](https://mlsanity.com/paper/2311.01388/) (2023)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [Variational Flow Graphical Model](https://mlsanity.com/paper/2207.02722/) (2022)
- [A Mutation-based Text Generation for Adversarial Machine Learning Applications](https://mlsanity.com/paper/2212.11808/) (2022)
- [TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks](https://mlsanity.com/paper/2604.06765/) (2026)
- [Deep Fake Detection, Deterrence and Response: Challenges and Opportunities](https://mlsanity.com/paper/2211.14667/) (2022)

## Abstract (arXiv)

Training generative models that can generate high-quality text with sufficient diversity is an important open problem for Natural Language Generation (NLG) community. Recently, generative adversarial models have been applied extensively on text generation tasks, where the adversarially trained generators alleviate the exposure bias experienced by conventional maximum likelihood approaches and result in promising generation quality. However, due to the notorious defect of mode collapse for adversarial training, the adversarially trained generators face a quality-diversity trade-off, i.e., the generator models tend to sacrifice generation diversity severely for increasing generation quality. In this paper, we propose a novel approach which aims to improve the performance of adversarial text generation via efficiently decelerating mode collapse of the adversarial training. To this end, we introduce a cooperative training paradigm, where a language model is cooperatively trained with the generator and we utilize the language model to efficiently shape the data distribution of the generator against mode collapse. Moreover, instead of engaging the cooperative update for the generator in a principled way, we formulate a meta learning mechanism, where the cooperative update to the generator serves as a high level meta task, with an intuition of ensuring the parameters of the generator after the adversarial update would stay resistant against mode collapse. In the experiment, we demonstrate our proposed approach can efficiently slow down the pace of mode collapse for the adversarial text generators. Overall, our proposed method is able to outperform the baseline approaches with significant margins in terms of both generation quality and diversity in the testified domains.