AI RESEARCH
Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models
arXiv CS.CL
•
ArXi:2604.07749v1 Announce Type: new Large language models (LLMs) can shift their answers under pressure in ways that reflect accommodation rather than reasoning. Prior work on sycophancy has focused mainly on disagreement, flattery, and preference alignment, leaving a broader set of epistemic failures less explored. We