4 papers
Specificity Bias and the Wikipedia Paradox: An xAI Analysis of AI Text Detectors under Domain Shift
Nico Morloher, Johannes Reschke, Mohamed Mady
The widespread adoption of Large Language Models (LLMs) demands reliable detection of human-authored versus synthetic text. However, current Transformer-based detectors often exper…
DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
Mohamed Mady, Yupei Li, Johannes Reschke +1
Robust detection of AI-generated text under deployment conditions is challenging: distribution shifts across domains and generators, adversarial perturbations of the input surface,…
Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models
Yupei Li, Qiyang Sun, Mohamed Mady +4
Large Audio Language Models (LALMs) have shown strong performance on audio reasoning benchmarks, but accuracy alone cannot distinguish true reasoning from superficial pattern match…
Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators
Mohamed Mady, Johannes Reschke, Björn Schuller
AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised…