@inproceedings{choi-zu-2025-exploring,
    title = "Exploring the Interpretability of {AI}-Generated Response Detection with Probing",
    author = "Choi, Ikkyu  and
      Zu, Jiyun",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.aimecon-sessions.12/",
    pages = "99--106",
    ISBN = "979-8-218-84230-7",
    abstract = "Multiple strategies for AI-generated response detection have been proposed, with many high-performing ones built on language models. However, the decision-making processes of these detectors remain largely opaque. We addressed this knowledge gap by fine-tuning a language model for the detection task and applying probing techniques using adversarial examples. Our adversarial probing analysis revealed that the fine-tuned model relied heavily on a narrow set of lexical cues in making the classification decision. These findings underscore the importance of interpretability in AI-generated response detectors and highlight the value of adversarial probing as a tool for exploring model interpretability."
}