Developing Virtual Personas from User Level Social Media Data
This paper tests the stability and human alignment of virtual patient profiles built from anonymized social media histories. Results vary across models, prompts, and clinical domains.
Human AI Interaction
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
This paper introduces PsychoSafe, a refusal framework grounded in evidence-based intervention strategies, and evaluates prompting and fine-tuning approaches for psychologically informed LLM refusals.
How do people develop folk theories of generative AI text-to-image models?
This paper presents a qualitative study exploring how people develop folk theories to explain and understand generative AI text-to-image models.
How do people experience the images created by generative artificial intelligence?
This paper explores how people experience images created by generative AI, examining their perceptions, appraisals, and emotional responses to GenAI text-to-image models and their creations.