{
  "id": "constitutional-classifiers",
  "code": "PTL-0168",
  "term": "Constitutional Classifiers",
  "aliases": [],
  "category": "security",
  "definition": "Constitutional classifiers are input and output safeguard classifiers trained on synthetic data generated from a written constitution that defines permitted and restricted content, designed to block universal jailbreaks.",
  "description": "Because the training data is generated from natural-language rules, the classifiers can be updated as threats change by editing the constitution. Their authors reported that thousands of hours of red teaming found no universal jailbreak against the protected system, at a modest cost in refusals and compute.",
  "example": null,
  "broader": [
    "guardrails"
  ],
  "narrower": [],
  "related": [
    "constitutional-ai",
    "jailbreak",
    "red-teaming"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming",
      "authors": "Sharma et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2501.18837"
    }
  ],
  "url": "https://protologue.com/t/constitutional-classifiers/",
  "citation": "Protologue. (2026). Constitutional Classifiers. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0168). https://protologue.com/t/constitutional-classifiers/"
}