This paper proposes a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation, and introduces a task-specific module that adapts the globally aligned persona set to targeted subpopulations.
Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like market research, public polling, preference elicitation, and social science research. However, evaluating AI interviewers is challenging because they function in extended, multi-turn interactions where they must adapt...
Jonathan Ivey, Aimee Liang, Arthur Y. S. Wang et al.· 1 citation
Everyday human-LLM interaction is not only answer delivery or cognitive offloading; it also contains measurable, selective and conditionally organized behavioural signatures of informal learning, which shift AI evaluation toward the preservation of cognitive opportunities for users to reason, test ideas and construct u...