NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

Title:NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution

Abstract:We present this http URL, an explainable AI-generated text detection system. Instead of returning only a binary label or confidence score, the system shows which signals influenced the prediction and lets users inspect an attribution-based sensitivity estimate obtained by subtracting selected local contributions. this http URL combines sentence-level conditional probability curvature, a neural detector score, and interpretable stylometric and readability features in an XGBoost meta-classifier. It explains predictions with TreeSHAP feature contributions and can turn the resulting evidence into a concise natural-language explanation. We evaluate the system on a category-balanced subset of RAID containing human-written, clean AI-generated, and attacked AI-generated texts. The full model outperforms variants based on individual feature families, reaching 0.9685 F1 on the held-out within-subset test split. In an automatic evaluation, two model judges rate 94.5-98.6\% of generated explanations as faithful to the supplied detector evidence. The web interface (this https URL), source code (this https URL), and demonstration video(this https URL) are publicly available.

Computation and Language (cs.CL)

arXiv:2603.05617 [cs.CL]

(or arXiv:2603.05617v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2603.05617 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.