Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators

Mohamed Mady, Johannes Reschke, Björn Schuller|May 5, 2026arXiv

Key Takeaway

AI-text detectors need feature augmentation and careful threshold calibration to work reliably across different domains and generators; linguistic features like readability are crucial for robustness under distribution shift.

Summary

This paper tackles the challenge of detecting AI-generated text across different domains and AI models. Researchers trained transformer-based detectors and found that while they perform nearly perfectly on their training data, they struggle when tested on new domains or text from different AI generators.

evaluation safety architecture

Key Terms

distribution-shift balanced-accuracy feature-augmentation deberta zero-shot-baseline