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

2026-03-05

AI Summary

This work proposes a high-accuracy, interpretable method for detecting AI-generated text. Addressing the challenge of distinguishing between human- and AI-authored content, we introduce a multidimensional feature framework that integrates conditional probability curvature, neural activation patterns, and stylometric metrics, employing XGBoost as the meta-classifier. Notably, this is the first study to incorporate curvature signals into detection tasks. To enhance interpretability, we apply SHAP for feature attribution and further leverage large language models to translate these attributions into structured natural language explanations, substantially improving result comprehensibility. The system supports real-time visual analysis and evidence presentation, and both the code and an interactive demonstration platform have been open-sourced to facilitate reproducibility and practical deployment.

Technology Category

Humans and AI: Explainable AI (XAI) for Human UnderstandingNatural Language Processing: Interpretability, Analysis, and Evaluation of NLP ModelsMachine Learning: Transparent, Interpretable, Explainable ML

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsWeb Mining and Content Analysis: Large pretrained models with web dataSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting. The system combines 17 interpretable features, including Conditional Probability Curvature, ModernBERT detector score, readability metrics, and stylometric cues, within a gradient-boosted tree (XGBoost) meta-classifier to determine whether a text is human- or AI-generated. Furthermore, NOTAI.AI applies Shapley Additive Explanations (SHAP) to provide both local and global feature-level attribution. These attributions are further translated into structured natural-language rationales through an LLM-based explanation layer, which enables user-facing interpretability. The system is deployed as an interactive web application that supports real-time analysis, visual feature inspection, and structured evidence presentation. A web interface allows users to input text and inspect how neural and statistical signals influence the final decision. The source code and demo video are publicly available to support reproducibility.

Problem

• machine-generated text detection
• explainable AI
• text attribution
• AI-generated content
• detectability

Innovation

• Explainable AI
• Curvature-based detection
• Feature attribution
• Stylometric analysis
• SHAP explanations