Beyond argumentation: AI-powered Socratic dialogue and political moderation in public deliberation

I examine whether AI-guided reasoning reduces issue polarization in two preregistered exper-iments conducted on deliberation.io, a purpose-built platform for deliberation research, with 5,000 participants across contentious U.S. policy issues. Relative to reflective writing,AI-emotional regulation, and AI-grammar correction, AI-Socratic dialogue —which promptsusers to articulate supporting arguments— significantly moderates extreme positions on mental health-based gun regulation. A second experiment comparing AI-Socratic dialogue to AI-grammar correction across abortion, handgun regulation, and voter ID requirements finds thatextreme participants moderate their positions and exhibit behavioral changes, including in-creased cross-partisan donations and reduced endorsement of extreme comments. Moderationeffects are largest for abortion, where baseline cross-partisan agreement was highest, and con-centrate among participants with low initial confidence, high susceptibility to elite cues, andlimited cross-party interactions.

Text analysis of conversational transcripts reveals that moderation operates through increased consideration of alternative perspectives rather than improvedargument quality, challenging standard deliberative theory. One-month follow-up displays mixedpersistence and minimal spillovers to untreated issues, consistent with issue-specific effects. Perceived agency remains equivalent across conditions, suggesting preserved autonomy. Overall, results indicate that AI conversational agents can facilitate compromise through previously un-derexplored mechanisms, offering promising scalable applications