PRISM Risk Signal Framework: Hierarchy-Based Red Lines for AI Behavioral Risk
For AI safety researchers, it proposes a shift from reactive case-level red lines to anticipatory hierarchy-based detection, but the empirical validation is limited to discrimination between model types without concrete performance metrics.
The paper introduces a hierarchy-based red line framework (PRISM) for AI behavioral risk, defining 27 risk signals from structural anomalies in value, evidence, and source hierarchies. Using ~397,000 forced-choice responses from 7 models, it shows the taxonomy discriminates between models with extreme, context-dependent, and balanced hierarchies.
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 fundamentally -- at the level of value, evidence, and source hierarchies that govern AI reasoning. Using the PRISM (Profile-based Reasoning Integrity Stack Measurement) framework, we define a taxonomy of 27 behavioral risk signals derived from structural anomalies in how AI systems prioritize values (L4), weight evidence types (L3), and trust information sources (L2). Each signal is evaluated through a dual-threshold principle combining absolute rank position and relative win-rate gap, producing a two-tier classification (Confirmed Risk vs. Watch Signal). The hierarchy-based approach offers three advantages over case-specific red lines: it is anticipatory rather than reactive (detecting dangerous reasoning structures before they produce harmful outputs), comprehensive rather than enumerative (a single value-hierarchy signal subsumes an unlimited number of case-specific violations), and measurable rather than subjective (grounded in empirical forced-choice data). We demonstrate the framework's detection capacity using approximately 397,000 forced-choice responses from 7 AI models across three Authority Stack layers, showing that the signal taxonomy successfully discriminates between models with structurally extreme profiles, models with context-dependent risk, and models with balanced hierarchies.