Group ethics training system uses ai agents for guided discussions
Ethics Training Agents: Facilitating Group-Based Ethics Education with Role-Playing and Discussion for Ethical Reflection and Exploration
Human-Computer Interaction
Summary
Ethics training for STEM students often requires lots of time and experts. The authors created a system where AI agents act with different ethical views to help students discuss and think about ethical problems together. They tested this with 45 students and found it helped people participate better and understand different viewpoints. The AI system also encouraged greater awareness of ethical issues.
What this means in practice
- •For corporate ethics trainers: Provide group ethics workshops with AI-driven role-playing agents that simulate diverse ethical viewpoints for better participant engagement.
- •For online learning platform developers: Integrate multi-agent ethics discussion tools into online STEM courses to support collaborative ethical reflection.
Authors
Youngseok Seo, Sueun Jang, Hyesoo Park, Renz Samuel Gutierrez, Joseph Seering, Uichin Lee
Abstract
Group-based ethics training for Science, Technology, Engineering and Mathematics (STEM) students is a complex challenge, requiring substantial resources and expertise. While activity-based teaching methods, such as role-playing and discussions, are commonly employed to simulate real-world scenarios, current practices are often manual and lack integration with effective online platforms for supporting group-based ethical discussions. In this work, we propose Ethics Training Agents, a group discussion system that leverages multiple LLM participants embodying distinct ethical orientations, along with a moderator agent, to enable structured human-AI group ethical discussions for collaborative reflection. We conduct a user study with 45 undergraduate STEM students to evaluate the learning outcomes and user experience. The results show that our system supports engagement, coordination, and perspective-taking in group discussions and has a positive influence on ethical sensitivity. We also discuss practical design strategies for integrating multiple LLM agents into multi-human group settings to facilitate ethics training for STEM students.