3 papers
cs.AI2026
Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models
Seulki Lee
What values, evidence preferences, and source trust hierarchies do AI systems actually exhibit when facing structured dilemmas? We present the first large-scale empirical mapping o…
cs.AI2026
PRISM Risk Signal Framework: Hierarchy-Based Red Lines for AI Behavioral Risk
Seulki Lee
Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines can be set more fundamental…
cs.AI2026
AI Integrity: A New Paradigm for Verifiable AI Governance
Seulki Lee
AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safety, and AI Alignment -- share…