Interactive ai system uses personas for fair policy debates
OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas
Artificial Intelligence
Summary
Discussions about important policies can be difficult and biased, especially when computers use language to help. The authors created OmouAI, a tool where people debate alongside computer-generated characters that represent different viewpoints. Each character suggests arguments, and users can add or change these, helping keep the conversation honest and balanced. The system checks how arguments affect goals like the UN Sustainable Development Goals, so users get clear explanations about the impact of each policy idea.
What this means in practice
- •For policy makers: Use the system to explore diverse stakeholder views and evaluate policy impacts with clear explanations during decision making.
- •For public engagement teams: Employ interactive personas to facilitate inclusive debates that represent various community opinions in public consultations.
Authors
Stylianos Loukas Vasileiou, Antonio Rago, William Yeoh, Georgina Curto
Abstract
Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions include humans and take place in high-stakes environments, e.g., in public policy deliberations, they are beset with issues such as sycophancy and a lack of faithful explanations. To tackle these issues, we present OmouAI, an interactive and inclusive deliberation system that uses LLMs in combination with computational argumentation, a field which excels in representing and reasoning within debates. OmouAI allows a human user to deliberate policy claims for real-world challenges with simulated personas, e.g., representing stakeholders, domain experts or devil's advocates, towards reducing sycophancy. Each persona generates its own arguments, and the arguments of all parties form a shared argumentation framework. Users can then contest, add and revise arguments, providing crucial human oversight. Then, arguments are evaluated using deterministic argumentative semantics against external goals, such as the UN Sustainable Development Goals, guaranteeing faithful explanations. The advancement or worsening of the goals thus serve as indicators for the policy recommendations.