Correction or Manipulation? Measuring Epistemic Vigilance in LLM Agents Under User Pressure
arXiv:2610.36453v1 Announce Type: new Abstract: LLM agents that answer questions and act on behalf of users must decide when to yield to a user who disagrees. Disagreement may correct a genuine error or may be an attempt at manipulation....
Read more: https://arxiv.org/abs/2610.36453
Scan with your phone
Scan with your phone