דגימות אישיות מנתחות: תוצאות של סימולציות סקרים בהתאם למצבי גישה לנתונים

תקציר מקורי באנגליתarXiv:2610.05828v2 Announce Type: replace Abstract: Large language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially reducing the cost and time of traditional surveys. However, many existing steering approaches rely on target-domain human data for fine-tuning or prompting that is costly to collect and raises privacy concerns. In this paper, we study demographic group-level survey simulation, where personas induced from heterogeneous, anonymized public behavioral data condition agents that simulate responses of individuals from specific demographic groups. We examine whether representative personas can be induced from diverse sources and analyze how the domain, scale, and granularity of the source data affect surv