LLM-generated messages can persuade humans on policy issues
Authors: H Bai, JG Voelkel, S Muldowney, JC Eichstaedt
Published: 2025
Publication: Nature ..., 2025 - nature.com
LLM-generated messages can effectively persuade humans on policy issues similarly to human-crafted messages, with differences in perceived persuasion mechanisms.
Methods: Three pre-registered experiments were conducted comparing the persuasive effectiveness of LLM-generated and human-generated messages on policy attitudes, using control conditions with neutral messages.
Key Findings: Influence of LLM-generated messages on participants' policy attitudes and perceived characteristics of the message authors.
Limitations: The study may not generalize beyond the specific policy issues tested and relies on participant self-reports about perceptions of message authors.
Institution: Stanford University
Research Area: Political Persuasion, LLM
Discipline: Computational Social Science
Sample Size: 4829 participants
Citations: 37