Who Sees the Risk? Stakeholder Conflicts and Explanatory Policies in LLM-based Risk Assessment
This work addresses the need for transparent and interpretable risk assessments in AI deployment, particularly for domains like medical AI, autonomous vehicles, and fraud detection, though it appears incremental as it builds on existing methods like Risk Atlas Nexus and GloVE.
The paper tackled the problem of understanding how different stakeholders perceive risks in AI systems by presenting a framework for stakeholder-grounded risk assessment using LLMs to predict and explain risks, showing that stakeholder perspectives significantly influence risk perception and conflict patterns.
Understanding how different stakeholders perceive risks in AI systems is essential for their responsible deployment. This paper presents a framework for stakeholder-grounded risk assessment by using LLMs, acting as judges to predict and explain risks. Using the Risk Atlas Nexus and GloVE explanation method, our framework generates stakeholder-specific, interpretable policies that shows how different stakeholders agree or disagree about the same risks. We demonstrate our method using three real-world AI use cases of medical AI, autonomous vehicles, and fraud detection domain. We further propose an interactive visualization that reveals how and why conflicts emerge across stakeholder perspectives, enhancing transparency in conflict reasoning. Our results show that stakeholder perspectives significantly influence risk perception and conflict patterns. Our work emphasizes the importance of these stakeholder-aware explanations needed to make LLM-based evaluations more transparent, interpretable, and aligned with human-centered AI governance goals.