Responsibility in Multi-Agent Sequential Decision-Making: Comparing Human Judgments to Formal Models of Causal Attribution
This work informs the development of AI systems that need to explain or attribute responsibility in multi-agent settings, though the findings are domain-specific and incremental.
The authors investigate how formal responsibility attribution models align with human judgments in multi-agent sequential decision-making scenarios, using a modified Goofspiel card game and a large-scale survey. They find that no single formal method consistently matches human judgments, but identify factors such as agent-specific biases and information availability that influence human responsibility assessments.
With the growing adoption of artificial intelligence in high-stakes decision-making, identifying the causes of outcomes--particularly failures--and determining who is responsible has become a critical concern. In this work, we examine how well formal definitions of \textit{responsibility attribution}, grounded in the framework of \textit{actual causality}, align with human judgments of responsibility. To this end, we conduct a large-scale survey to elicit human judgments of responsibility in multi-agent sequential decision-making scenarios, using a modified version of the card game Goofspiel. We evaluate multiple responsibility attribution methods, assess their alignment with human judgments about responsibility, and identify factors that significantly shape responsibility judgments. While no single responsibility attribution method consistently aligns with human responses, our findings highlight key factors that influence human responsibility judgments, including agent-specific biases and amount of information available to agents during decision-making.