Tag
This paper introduces a controlled content overlap setup using parallel Bible translations to evaluate how much style classifiers rely on content cues rather than actual style features. Results show that low-overlap models degrade when content cues are removed, while high-overlap models transfer more robustly.
This paper demonstrates that fine-tuned AI text detectors amplify a pretrained typicality axis rather than learning an AI-vs-human boundary, with raw encoder projections often matching or exceeding fine-tuned performance.
ETH Zurich researchers show that fine-tuned RoBERTa models can infer users’ Big-Five personality traits from ChatGPT chat logs with up to 44 % above-random accuracy, highlighting privacy risks of conversational AI.