AI-text detectors
PulseAugur coverage of AI-text detectors — every cluster mentioning AI-text detectors across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New RL attack evades multiple AI text detectors
Researchers have developed StealthRL, a reinforcement learning framework designed to test the robustness of AI-text detectors against adversarial paraphrasing. This method trains an attack policy to generate meaning-pre…
-
AI text detectors show high false positives for non-native academic writing
A new study published on arXiv investigates the reliability of AI text detectors in academic settings, particularly for non-native English writers. Researchers analyzed over 135,000 document pairs from a professional ed…
-
AI text detectors amplify bias, not learn AI vs human
A new research paper suggests that AI text detectors do not learn to distinguish between AI-generated and human-written text. Instead, these detectors amplify a pre-existing directional bias in their training data, effe…