Causal Responsibility Attribution for Human-AI Collaboration

TL;DR

This paper introduces a causal framework using Structural Causal Models to attribute responsibility in human-AI collaborations, addressing limitations of existing methods by incorporating counterfactual reasoning and epistemic considerations.

Contribution

It proposes a novel causal attribution framework for human-AI systems that accounts for blameworthiness and epistemic states, improving responsibility assignment accuracy.

Findings

Framework effectively attributes responsibility in diverse scenarios

Counterfactual reasoning enhances blameworthiness assessment

Case studies demonstrate adaptability of the approach

Abstract

As Artificial Intelligence (AI) systems increasingly influence decision-making across various fields, the need to attribute responsibility for undesirable outcomes has become essential, though complicated by the complex interplay between humans and AI. Existing attribution methods based on actual causality and Shapley values tend to disproportionately blame agents who contribute more to an outcome and rely on real-world measures of blameworthiness that may misalign with responsible AI standards. This paper presents a causal framework using Structural Causal Models (SCMs) to systematically attribute responsibility in human-AI systems, measuring overall blameworthiness while employing counterfactual reasoning to account for agents' expected epistemic levels. Two case studies illustrate the framework's adaptability in diverse human-AI collaboration scenarios.