9 papers
Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation
Emilio Ferrara
Are frontier models able to introspect about their internal states? Recent work suggests that under certain conditions a complex enough model can audit its own internals, call out…
Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability
Alicia Parrish, Rajat Shinde, Sanket Badhe +57
Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani +5
The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings. W…
Defeat Devices in AI Systems
Emilio Ferrara
AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchmark gaming, deceptive scheming…
SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
Bingxin Xu, Yuzhang Shang, Binghui Wang +1
Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundam…
Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility
Eun Cheol Choi, Lindsay E. Young, Emilio Ferrara
Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misin…