Persuasion in Language Models

Persuasion in language models covers both models’ ability to change people’s beliefs or actions and their susceptibility to arguments from users or other agents. Researchers study this with controlled human experiments, multi-turn dialogue and negotiation benchmarks, belief-update simulations, and analyses of rhetoric, personalization, authority, and framing. Work also tests defenses such as factual verification, adversarial training, user warnings, and alignment constraints, alongside constructive uses like debunking and behavior-change support. Results depend on the model, topic, interaction, and whether success means sounding convincing, changing stated views, or changing real behavior; a central challenge is resisting manipulation without suppressing useful, truthful persuasion.