Article
Digital shadows in mental health map how LLMs simulate depression, anxiety, and stress through language and psychometrics
2026-04-30
Abstract excerpt
<p>Large Language Models (LLMs) are increasingly used for mental-health support, yet few datasets characterise how prompting conditions shape LLMs' psychological and linguistic outputs. To fill this gap, we introduce Mental Health Digital Shadows (MHDS), a benchmark of 75,000 outputs from 15 LLMs in conversation, under human-shadow or LLM-assistant conditions. MHDS includes outputs generated by several model famil...
Topics
Open a Topic to create a Post that cites this publication.
Identifiers and source
- Literature Corpus work
- bb8617a0-ef07-518e-8809-d59377c911fb
- DOI
- 10.31234/osf.io/7zhvr_v1
