# PRISM Risk Signal Framework: Hierarchy-Based Red Lines for AI Behavioral Risk

arXiv: https://arxiv.org/abs/2604.11070 · HTML: https://mlsanity.com/paper/2604.11070/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [The science and practice of proportionality in AI risk evaluations](https://mlsanity.com/paper/2603.10017/) (2026)

## Abstract (arXiv)

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.