Substantive LLM reframing boosts cross-partisan receptivity to news headlines without backfire, but models overestimate effect sizes and lack fidelity in modeling human psychological responses.
These effects among conservative silicon participants were substantially larger than the corresponding human effects across all outcomes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness
Substantive LLM reframing boosts cross-partisan receptivity to news headlines without backfire, but models overestimate effect sizes and lack fidelity in modeling human psychological responses.