7 citations · 8 across the 7 of their papers we have counts for
3 papers · 1 filter
Limits of LLM Text Detectors in Education
Lukas Gehring, Benjamin Paaßen
Students increasingly use the assistance of large language models (LLMs) in their academic writing. While slight assistance (e.g., grammar and style correction, as well as feedback…
Diffusion Classifier Guidance for Non-robust Classifiers
Philipp Vaeth, Dibyanshu Kumar, Benjamin Paassen +1
Classifier guidance is intended to steer a diffusion process such that a given classifier reliably recognizes the generated data point as a certain class. However, most classifier…
Healthy Distrust in AI systems
Benjamin Paaßen, Suzana Alpsancar, Tobias Matzner +1
Under the slogan of trustworthy AI, much of contemporary AI research is focused on designing AI systems and usage practices that inspire human trust and, thus, enhance adoption of…