Persuasive Argument
Persuasive argumentation research focuses on understanding and modeling how language influences beliefs and actions, aiming to quantify and improve the effectiveness of persuasive communication. Current research employs large language models (LLMs) like GPT-4 and architectures incorporating techniques such as prompt tuning, multi-modal analysis (combining text and images), and reinforcement learning to analyze and generate persuasive text across various domains, including political discourse and e-commerce. This work has significant implications for understanding and mitigating the societal impact of AI-generated persuasive content, informing the development of responsible AI systems, and improving the design of persuasive communication in various fields.
Papers
Evidence of a log scaling law for political persuasion with large language models
Kobi Hackenburg, Ben M. Tappin, Paul Röttger, Scott Hale, Jonathan Bright, Helen Margetts
Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking
Mohamed Elaraby, Diane Litman, Xiang Lorraine Li, Ahmed Magooda