8 papers
DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
Jared Moore, Andrea Mock, Yifan Mai +9
Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including "delusional spirals" in which conce…
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
Jared Moore, Noah Goodman, Nick Haber +1
Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change. These endpoint measures identify whether persu…
The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue
Ashish Mehta, Jared Moore, Jacy Reese Anthis +6
There is growing concern that AI chatbots might fuel delusional beliefs in users. Some have suggested that humans and chatbots mutually reinforce false beliefs over time, but quant…
Verbalizing LLMs' assumptions to explain and control sycophancy
Myra Cheng, Isabel Sieh, Humishka Zope +7
LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment. We hypothesize that this behavior aris…
Characterizing Delusional Spirals through Human-LLM Chat Logs
Jared Moore, Ashish Mehta, William Agnew +11
As large language models (LLMs) have proliferated, disturbing anecdotal reports of negative psychological effects, such as delusions, self-harm, and ``AI psychosis,'' have emerged…
Large Language Models Persuade Without Planning Theory of Mind
Jared Moore, Rasmus Overmark, Ned Cooper +3
A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive question-and-answer benchmar…