Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers

ArXi:2601.07698v2 Announce Type: replace As emotional chatbots have recently gained significant traction across both research and industry, a common evaluation strategy has emerged: use help-seeker simulators to interact with er chatbots. However, current simulators suffer from two critical limitations: (1) they fail to capture the behavioral diversity of real-world seekers, often portraying them as overly cooperative, and (2) they lack the controllability required to simulate specific seeker profiles.