← Back to Model Beat
Open Source·4d ago·all news from November 18, 2026

AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion

arXiv:2411.10109v4 Announce Type: replace Abstract: AI simulations of people built from demographic prompts often misjudge individuals and distort sample-level patterns. We test whether rich self-report data reduce these problems. We developed an AI voice interviewer and conducted two-hour interviews following the American Voices Project protocol with 1,052 U.S. adults, who also completed surveys and behavioral experiments. For each participant, we compared simulations prompted with demographic attributes, self-authored personas, survey responses, interview responses, or combined surveys and interviews. We evaluated accuracy on held-out responses, and measured eight statistical distortions at the sample level: biased averages, compressed variance, distorted response distributions, over-correlated items, attitudes collapsing onto one dimension, ideological sorting, amplified experimental effects, and hyper-rationality. On General Social Survey (GSS) items, demographic simulation led to 60.4% accuracy, whereas interview and survey simulation achieved 69.4% and 69.3%, and combining them reached 72.8%, compared with 79.5% for participants' two-week test-retest agreement. Surveys and interviews…

Covered by 1 source

  • AarXiv CS.AI↗Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst, Niles Egan, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Percy Liang, Robb Willer, Michael S. Bernstein4d ago

Related stories

Open SourceReports of AI-generated child sexual abuse material have surged more than 8,400 percent in two yearsNov 16 · 3 sourcesOpen SourceHugging Face and OpenRouter join forces to make open-weight models easy to runNov 16Open SourceRunway's open-source Praxis-1 turns video AI into a robot controllerNov 14Open SourceAt Holiday Extras, dots get to work before anyone asksNov 16