@inproceedings{kuznetsov-etal-2024-robust,
    title = "Robust {AI}-Generated Text Detection by Restricted Embeddings",
    author = "Kuznetsov, Kristian  and
      Tulchinskii, Eduard  and
      Kushnareva, Laida  and
      Magai, German  and
      Barannikov, Serguei  and
      Nikolenko, Sergey  and
      Piontkovskaya, Irina",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-emnlp.992/",
    doi = "10.18653/v1/2024.findings-emnlp.992",
    pages = "17036--17055",
    abstract = "Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-generated text, namely their ability to transfer to unseen generators or semantic domains. We investigate the geometry of the embedding space of Transformer-based text encoders and show that clearing out harmful linear subspaces helps to train a robust classifier, ignoring domain-specific spurious features. We investigate several subspace decomposition and feature selection strategies and achieve significant improvements over state of the art methods in cross-domain and cross-generator transfer. Our best approaches for head-wise and coordinate-based subspace removal increase the mean out-of-distribution (OOD) classification score by up to 9{\%} and 14{\%} in particular setups for RoBERTa and BERT embeddings respectively. We release our code and data: https://github.com/SilverSolver/RobustATD"
}