Spoken Argumentation

Spoken argumentation research focuses on computationally modeling and analyzing the structure and persuasiveness of arguments expressed in spoken language, aiming to improve automated argument understanding and generation. Current research emphasizes developing robust evaluation methods for automatically generated arguments, particularly in specialized domains like medicine and law, and exploring the use of large language models (LLMs) and argumentation frameworks (AFs) to analyze implicit reasoning, detect bias, and generate context-appropriate explanations. This field is significant for advancing AI capabilities in natural language processing, improving human-computer interaction, and offering tools for analyzing and mitigating biases in online discourse and other applications.