Building on work from our 2023-2024 Bots vs. Ballots Collaboratory, this research team will design, develop, and prototype a large language model-powered chatbot aimed at countering far-right hate speech and misinformation online. The team will develop a framework that allows the bot to identify and address specific forms of hate speech and implement a particular style of engagement for the bot to effectively promote alternative narratives.
Our team is an interdisciplinary group of students, faculty, and Lab staff interested in developing artificial intelligence by integrating insights from various fields. Students include those with expertise in AI development as well as those from the humanities and social sciences who offer crucial insights into the thoughtful application of language and culture in confronting the discourse of hate speech.