AHFE Open AccessLeveraging Multi-User Dungeons for Ethical AI Decision Support Systems: A Novel Approach
Abstract
This paper proposes the innovative use of Multi-User Dungeons (MUDs) as a testbed for exploring and refining Artificial Intelligence (AI) ethics in decision support systems. MUDs are interactive, text-based virtual environments and offer a unique platform for studying AI behavior in a controlled yet complex environment. Our approach involves a combination of machine learning and natural language processing techniques to implement AI as a decision support system, and designs scenarios that challenge players with ethical quandaries and dilemmas. The effectiveness and ethical decision-making of players, the AI, and both together as a team are evaluated through a mix of quantitative and qualitative methods. The approaches detailed in this research aim to contribute to the broader discourse on AI ethics, stimulate a discussion on how to provide empirical evidence of AI decision-making's impact on human behavior in MUDs, and informing the design of ethically responsible AI systems in other domains.
Keywords: Artificial Intelligence Ethics, Multi-User Dungeons (MUDs), Human-AI Interaction
DOI: 10.54941/ahfe1004180
Cite this paper
More from this volume
- CHAAIS: Climate-focused Human-machine teaming and Assurance in Artificial Intelligence Systems – Framework applied toward wildfire management case study
- The Evolution of AI on the Commercial Flight Deck: Finding Balance between Efficiency and Safety While Maintaining the Integrity of Operator Trust
- TAUCHI-GPT: Leveraging GPT-4 to create a Multimodal Open-Source Research AI tool
- A Survey of Beliefs and Attitudes toward Artificial Intelligence — Practical Implications and Fictional Depictions
- Exploring the Impact of Generative Artificial Intelligence on the Design Process: Opportunities, Challenges, and Insights
- Relationships among Personality Traits, ChatGPT Usage and Concept Generation in Innovation Design
- Measuring the Impact of Picture-Based Explanations on the Acceptance of an AI System for Classifying Laundry
- Automated generation of synthetic person activity data for AI models training
- Human-Animal Teaming as a Model for Human-AI-Robot Teaming: Advantages and Challenges
- A method to generate adversarial examples based on color variety of adjacent pixels
- Integrating Domain Expertise and Artificial Intelligence for Effective Supply Chain Management Planning Tasks: A Collaborative Approach
- User Trust Towards an AI-assisted Healthcare Decision Support System under Varied Explanation Formats and Expert Opinions