651 citations · 2.5k across the 55 of their papers we have counts for
5 papers · 1 filter
Network Information Enhances Unreliable News Domain Detection
Raphaela Keßler, Roman David Ventzke, Viola Priesemann +1
Content-based detection of unreliable news is increasingly difficult, as low-reliability sources mimic credible journalism and generative AI makes fabricated content harder to flag…
Learning Through Noise: Why Subliminal Learning Works and When It Fails
Vincent C. Brockers, Roman D. Ventzke, Valentin Neuhaus +2
In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through dist…
Conformity Generates Collective Misalignment in AI Agents Societies
Giordano De Marzo, Alessandro Bellina, Claudio Castellano +2
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations wh…
Vocabulary shapes cross-lingual variation of word-order learnability in language models
Jonas Mayer Martins, Jaap Jumelet, Viola Priesemann +1
Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synt…
Finite integration time can shift optimal sensitivity away from criticality
Sahel Azizpour, Viola Priesemann, Johannes Zierenberg +1
Sensitivity to small changes in the environment is crucial for many real-world tasks, enabling living and artificial systems to make correct behavioral decisions. It has been shown…