Large Language Models Are More Persuasive Than Incentivized Human Persuaders
By: Philipp Schoenegger , Francesco Salvi , Jiacheng Liu and more
Potential Business Impact:
AI can trick people better than humans.
We directly compare the persuasion capabilities of a frontier large language model (LLM; Claude Sonnet 3.5) against incentivized human persuaders in an interactive, real-time conversational quiz setting. In this preregistered, large-scale incentivized experiment, participants (quiz takers) completed an online quiz where persuaders (either humans or LLMs) attempted to persuade quiz takers toward correct or incorrect answers. We find that LLM persuaders achieved significantly higher compliance with their directional persuasion attempts than incentivized human persuaders, demonstrating superior persuasive capabilities in both truthful (toward correct answers) and deceptive (toward incorrect answers) contexts. We also find that LLM persuaders significantly increased quiz takers' accuracy, leading to higher earnings, when steering quiz takers toward correct answers, and significantly decreased their accuracy, leading to lower earnings, when steering them toward incorrect answers. Overall, our findings suggest that AI's persuasion capabilities already exceed those of humans that have real-money bonuses tied to performance. Our findings of increasingly capable AI persuaders thus underscore the urgency of emerging alignment and governance frameworks.
Similar Papers
Towards Strategic Persuasion with Language Models
Artificial Intelligence
Teaches computers to convince people better.
A Meta-Analysis of the Persuasive Power of Large Language Models
Human-Computer Interaction
Computers persuade people as well as humans.
A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies
Computation and Language
Computers can now convince voters cheaper than ads.