2 papers
cs.AI2026
When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare
Priyadarsi Mishra, Arjun Beniwal, Ziyu Yi +2
Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many consequential settings, one p…
cs.HC2026
CRiDiT: Instantiating a run-time testbed for trust calibration in AI-infused systems
Yuntian Ding, Nicolas Herbaut, Camille Salinesi
The integration of AI into larger technical infrastructures has made the alignment of human trust with system trustworthiness, known as trust calibration, a critical engineering co…