CounselBench introduces expert-rated evaluations and an adversarial test set showing LLMs frequently produce unconstructive, overgeneralized, or unsafe responses in mental health QA compared to human therapists.
Measuring inter-rater reliability for nominal data – which coefficients and confidence intervals are appropriate? BMC Medical Research Methodology, 16(1):93, December 2016
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
CounselBench introduces expert-rated evaluations and an adversarial test set showing LLMs frequently produce unconstructive, overgeneralized, or unsafe responses in mental health QA compared to human therapists.