Theme of inquiry

Why do models show mismatched confidence and reasoning across tasks?

A question within its area, explored through 4 lines of inquiry below — each a family of specific questions the research asks.


Can LLM personas constitute genuine psychology or remain linguistic role-play?

18 specific questions

See all 18 questions in this line of inquiry
What distinguishes dynamic from static grounding in dialogue systems?

10 specific questions

See all 10 questions in this line of inquiry
Is embodied interaction necessary for language meaning and genuine agency?

43 specific questions

See all 43 questions in this line of inquiry
How do LLMs distinguish causal reasoning from temporal and semantic associations?

39 specific questions

See all 39 questions in this line of inquiry