Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness

This research paper explores whether LLMs can debias partisan news to improve cross-partisan receptivity among conservative readers. It found that a substantive reframing by LLMs significantly increased conservatives' trust and willingness to engage with liberal news headlines, though LLMs overestimate their own effectiveness.