Fig. 1: Participants’ change in policy support by condition across studies.
From: LLM-generated messages can persuade humans on policy issues
Y-axes represent the average difference between participants’ post-treatment and pre-treatment policy support (both scaled from 0 to 100, 100 = highest level of support). Higher scores indicate participants became more supportive of the policy. Data are analyzed using regression, two-tailed, and results are presented as mean values with 95% confidence intervals. NStudy 1 = 1203 participants, NStudy 2 = 2016 participants, NStudy 3 = 1610 participants.
