Model Releases
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
arXiv:2510.12476v2 Announce Type: replace Abstract: Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this abi
arXiv:2510.12476v2 Announce Type: replace Abstract: Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no prior work has examined personalized machine-generated text (MGT) detection. In this paper, we introduce ataset, the first benchmark for evaluating detector robustness in personalized settings, built from literary and blog texts paired with their LLM-generated imitations. Our experimental results demonstrate large performance gaps across detectors in personalized settings: some state-of-the-art models suffer significant drops. We attribute this limitation to the extit{feature-inversion trap}, where features that are discriminative in general domains become inverted and misleading when applied to personalized text. Based on this finding, we propose method, a simple and reliable way to predict detector performance changes in personalized settings. method identifies latent directions corresponding to inverted features and constructs probe datasets that differ primarily along these features to evaluate detector dependence. Our experiments show that method can accurately predict both the direction and the magnitude of post-transfer changes, showing 85% correlation with the actual performance gaps. We hope that this work will encourage further research on personalized text detection.
Related
- Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
- Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
- Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs
- TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
Source: arXiv cs.CL | 2026-04-10