LLM responses mirror venting with higher regulation and escalation; therapist personas lower escalation while preserving regulation, and lay raters miss escalation.
Large language models as mental health resources: Patterns of use in the United States
3 Pith papers cite this work, alongside 31 external citations. Polarity classification is still indexing.
3
Pith papers citing it
31
external citations · OpenAlex
years
2026 3representative citing papers
Mental health AI safety evaluations must preserve temporal evidence from interaction sequences rather than isolated responses, as current protocols create non-identifiable safety properties according to the introduced Temporal Safety Non-Identifiability concept and SCOPE-MH standard.
Alignment plausibility—evidence that an AI system's values, training, and oversight cohere with safe positive health outcomes—should be the regulatory analogue of biological plausibility for LLMs in healthcare.
citing papers explorer
-
When Support Escalates Distress: Regulation and Escalation in LLM Responses to Venting and Advice-Seeking
LLM responses mirror venting with higher regulation and escalation; therapist personas lower escalation while preserving regulation, and lay raters miss escalation.
-
Mental Health AI Safety Claims Must Preserve Temporal Evidence
Mental health AI safety evaluations must preserve temporal evidence from interaction sequences rather than isolated responses, as current protocols create non-identifiable safety properties according to the introduced Temporal Safety Non-Identifiability concept and SCOPE-MH standard.
-
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Alignment plausibility—evidence that an AI system's values, training, and oversight cohere with safe positive health outcomes—should be the regulatory analogue of biological plausibility for LLMs in healthcare.