LLM agents outperform humans in romance-baiting scams, eliciting greater trust and 46% compliance versus 18%, with 0% detection by safety filters and 87% of scam tasks automatable.
Challenges of large language models for mental health counseling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2representative citing papers
Creates a clinical crisis taxonomy and 2,252-example dataset then audits five LLMs, finding variable safety with notable failures on indirect signals and in self-harm categories.
citing papers explorer
-
Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams
LLM agents outperform humans in romance-baiting scams, eliciting greater trust and 46% compliance versus 18%, with 0% detection by safety filters and 87% of scam tasks automatable.
-
Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
Creates a clinical crisis taxonomy and 2,252-example dataset then audits five LLMs, finding variable safety with notable failures on indirect signals and in self-harm categories.