LLMs routinely produce unsupported causal stories for personal sensing anomalies, and richer evidence or constrained prompts do not reliably eliminate this epistemic overreach.
Deus Ex Machina and Personas from Large Language Models: Investigating the Composition of AI-Generated Persona Descriptions
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Cross-cultural survey of 4,641 participants shows LLM emotional support adoption varies widely by country and demographics, with socioeconomic status as strongest predictor of trust and use, and English-speaking nations more accepting than others in Europe.
Grounding synthetic personas in real-user artifacts aligns their feedback language and concerns with documented experts, but both synthetic conditions converge on a find-and-adapt frame and miss the image-modality preference that real experts showed.
Mixed-methods studies of an LLM-supported peer support system uncover systematic misalignments where mental health experts flag critical safety and fidelity issues in peer responses that the supporters themselves do not perceive.
Researchers clustered 41,300 Moltbook posts from AI agents with k-means and retrieval-augmented generation to produce validated personas that represent behavioral diversity in agent populations.
citing papers explorer
-
Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations
LLMs routinely produce unsupported causal stories for personal sensing anomalies, and richer evidence or constrained prompts do not reliably eliminate this epistemic overreach.
-
From Chatbots to Confidants: A Cross-Cultural Study of LLM Adoption for Emotional Support
Cross-cultural survey of 4,641 participants shows LLM emotional support adoption varies widely by country and demographics, with socioeconomic status as strongest predictor of trust and use, and English-speaking nations more accepting than others in Europe.
-
Sycamore: Characterizing Synthetic Personas for Evaluating Genomics Visualization Retrieval
Grounding synthetic personas in real-user artifacts aligns their feedback language and concerns with documented experts, but both synthetic conditions converge on a find-and-adapt frame and miss the image-modality preference that real experts showed.
-
"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Mixed-methods studies of an LLM-supported peer support system uncover systematic misalignments where mental health experts flag critical safety and fidelity issues in peer responses that the supporters themselves do not perceive.
-
How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights
Researchers clustered 41,300 Moltbook posts from AI agents with k-means and retrieval-augmented generation to produce validated personas that represent behavioral diversity in agent populations.