# OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation

arXiv: https://arxiv.org/abs/2104.02484 · HTML: https://mlsanity.com/paper/2104.02484/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 13 of 13)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Out-of-domain Detection for Natural Language Understanding in Dialog Systems](https://mlsanity.com/paper/1909.03862/) (2019)
- [Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog](https://mlsanity.com/paper/1912.12800/) (2019)
- [Adversarial Text Generation Without Reinforcement Learning](https://mlsanity.com/paper/1810.06640/) (2018)
- [Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation](https://mlsanity.com/paper/1905.10247/) (2019)

## Built on by (most cited first, 15 of 15)

- [Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.15330/) (2024)
- [EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records](https://mlsanity.com/paper/2301.07695/) (2023)
- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Learning on Graphs with Out-of-Distribution Nodes](https://mlsanity.com/paper/2308.06714/) (2023)
- [GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation](https://mlsanity.com/paper/2109.03079/) (2021)
- [TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring](https://mlsanity.com/paper/2403.15879/) (2024)
- [Estimating Soft Labels for Out-of-Domain Intent Detection](https://mlsanity.com/paper/2211.05561/) (2022)
- [Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization](https://mlsanity.com/paper/2109.07968/) (2021)
- [Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts](https://mlsanity.com/paper/2305.03237/) (2023)
- [Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection](https://mlsanity.com/paper/2211.11255/) (2022)
- [A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery](https://mlsanity.com/paper/2303.04134/) (2023)
- [Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics](https://mlsanity.com/paper/2510.06505/) (2025)
- [Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)](https://mlsanity.com/paper/2205.11887/) (2022)
- [Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems](https://mlsanity.com/paper/2306.04823/) (2023)
- [Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation](https://mlsanity.com/paper/2509.20587/) (2025)

## Abstract (arXiv)

Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialog system. Most dialog systems are trained on a pool of annotated OOD data to achieve this goal. However, collecting the annotated OOD data for a given domain is an expensive process. To mitigate this issue, previous works have proposed generative adversarial networks (GAN) based models to generate OOD data for a given domain automatically. However, these proposed models do not work directly with the text. They work with the text's latent space instead, enforcing these models to include components responsible for encoding text into latent space and decoding it back, such as auto-encoder. These components increase the model complexity, making it difficult to train. We propose OodGAN, a sequential generative adversarial network (SeqGAN) based model for OOD data generation. Our proposed model works directly on the text and hence eliminates the need to include an auto-encoder. OOD data generated using OodGAN model outperforms state-of-the-art in OOD detection metrics for ROSTD (67% relative improvement in FPR 0.95) and OSQ datasets (28% relative improvement in FPR 0.95) (Zheng et al., 2020).