Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA

Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming· July 10, 2026 View original

▶ The 2-minute explainer

Summary

This research introduces Constitutional Meta-STPA, a framework for self-validating LLM-assisted safety analysis tools. It applies Systems-Theoretic Process Analysis (STPA) to the LLM tool itself, deriving a governance constitution to ensure safety, auditability, and prevent issues like hallucinated standards.

As Large Language Models (LLMs) are increasingly used to draft safety analysis artifacts within rigorous processes like Systems-Theoretic Process Analysis (STPA), a critical oversight has emerged: the LLM-assisted tool itself is rarely analyzed for safety. This paper addresses this gap by proposing "Constitutional Meta-STPA." This novel framework turns STPA onto the AI-assisted safety tool, creating a closed-loop system. It derives a governance constitution for the tool from its own meta-STPA analysis, establishing principles and safety guidelines that are bound to code enforcement points. The research demonstrates that frontier LLM ensembles can effectively self-derive these principles, highlighting the potential for AI to validate its own safety analysis processes and ensure auditability and reliability in critical applications.

Why it matters

Ensuring the safety and reliability of AI tools used in critical safety analyses is paramount for preventing catastrophic failures and building trust in AI-assisted decision-making processes.

How to implement this in your domain

  1. 1Adopt a meta-analysis framework for any AI tools used in safety-critical applications.
  2. 2Develop internal governance principles for LLM-assisted safety analysis, ensuring auditability.
  3. 3Integrate self-validation mechanisms into your AI safety tools to detect and mitigate hazards.
  4. 4Train your teams on the principles of Systems-Theoretic Process Analysis (STPA) for AI systems.

Who benefits

AerospaceAutomotiveHealthcareNuclear EnergyDefense

Key takeaways

  • LLM-assisted safety analysis tools must also be analyzed for safety.
  • Constitutional Meta-STPA provides a framework for self-validation.
  • The framework derives governance principles from the tool's own analysis.
  • This enhances the reliability and auditability of AI in safety-critical domains.

Original post by Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming

"arXiv:2607.08054v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs), and safety constraints, inside rigorous processes such as Systems-Theoretic Pro…"

View on X

Originally posted by Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research

AI Research

New Algorithm Learns AC^0 Circuits Under Correlated Distributions

Researchers present a quasipolynomial-time algorithm for learning constant-depth circuits (AC^0) under graphical models that allow efficient local sampling. This work extends prior guarantees by circumventing the polynomial-growth requirement, offering a framework applicable to two-spin systems on arbitrary bounded-degree graphs.

Weiming Feng, Xiongxin Yang, Yixiao Yu, Yiyao ZhangJul 10, 2026
AI ResearchAI Engineering & DevTools

AI System Recommends Pathological Tests, Improving Diagnostic Efficiency

A new study introduces a pathological test recommendation system using Classifier Chain (CC) techniques to suggest diagnostic tests based on patient symptoms before physician consultation. The system, leveraging machine learning and Explainable AI (XAI), achieved high accuracy and provided clinically interpretable reasoning consistent with medical knowledge.

Abu Rafe Md Jamil, Nayan MalakarJul 10, 2026
AI ResearchAI Engineering & DevTools

CASL-VAE Learns Latent Variables from Unpaired Data for Disease Analysis

Researchers introduce CASL-VAE, a deep contrastive latent variable model that learns structured latent generative factors from unpaired data to quantify population variability. It factorizes variation into common and hierarchical salient factors, enabling improved subtype recovery and paired-sample generation, validated on neuroimaging data for Alzheimer's disease.

Sai Spandana Chintapalli, Pratik Chaudhari, Christos DavatzikosJul 10, 2026