Persuasive Capability

Persuasive capability research investigates how language models generate and respond to persuasive messages, aiming to understand and measure their effectiveness across various domains. Current research focuses on developing benchmarks and algorithms to assess persuasiveness, exploring the role of model size and training data, and analyzing the use of different rhetorical strategies and linguistic features. This work is crucial for mitigating potential harms from manipulative AI while harnessing the positive applications of persuasive technologies in areas like public health and social good, informing both AI development and policy.