arXiv cs.AIPaper
Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
Confidence is the problem, not just accuracy. When an LLM is wrong and sounds certain, users learn the wrong thing, and belief in the falsehood spreads through the conversation. If you're building educational or advisory tools, this is a hard constraint: your users will defer to confident systems even when they should not. Calibrated uncertainty matters more than it feels like it should.