John Mendonça
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
According to the abstract excerpt, the authors present MindEval2, an evaluation framework for chatbots used in mental health support. It pairs rubrics developed with PhD-level psychologists with a simulated-patient harness, aiming to be more realistic and interpretable than earlier benchmarks.