As state-of-the-art language models continue to improve, the need for robust detection of machine-generated text becomes increasingly critical. However, current state-of-the-art machine text detectors struggle to adapt to new unseen domains and generative models. In this paper we present DoGEN (Domain Gating Ensemble Networks), a technique that allows detectors to adapt to unseen domains by ensembling a set of domain expert detector models using weights from a domain classifier. We test DoGEN on a wide variety of domains from leading benchmarks and find that it achieves state-of-the-art performance on in-domain detection while outperforming models twice its size on out-of-domain detection. We release our code and trained models to assist in future research in domain-adaptive AI detection.
@article{arxiv.2505.13855,
title = {Domain Gating Ensemble Networks for AI-Generated Text Detection},
author = {Arihant Tripathi and Liam Dugan and Charis Gao and Maggie Huan and Emma Jin and Peter Zhang and David Zhang and Julia Zhao and Chris Callison-Burch},
journal= {arXiv preprint arXiv:2505.13855},
year = {2025}
}