Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issues

ArXi:2603.20229v1 Announce Type: cross Traditional survey-based political issue polling is becoming less tractable due to increasing costs and risk of bias associated with growing non-response rates and declining coverage of key graphic groups. With researchers and pollsters seeking alternatives, Large Language Models have drawn attention for their potential to augment human population studies in polling contexts.