---
aliases:
  en:
  - AI control eval
  - AI control evaluation
  - control eval
  - control evaluations
concept_id: control_evaluation
preferred:
  en: control evaluation
relations:
  relations:
    broader:
    - evaluation
    prerequisite:
    - control_protocol
    - evaluation
    related:
    - red_teaming
status: active
---

# control evaluation

An adversarial evaluation of a control protocol that estimates its safety and usefulness under pessimistic assumptions about untrusted-model behavior, typically by having a red team construct adversarial substitutes for untrusted models and measuring whether they can cause a specified unacceptable outcome without being caught.

## broader

- [evaluation](../terminology/evaluation.txt)

## prerequisite

- [control protocol](../terminology/control_protocol.txt)
- [evaluation](../terminology/evaluation.txt)

## related

- [red teaming](../terminology/red_teaming.txt)

## Documents: mentions

- [control safety caseには、能力の十分な引き出しと、評価・外挿の保守性が必要になる](../documents/korbak_et_al.control-safety-cases-depend-on-elicitation-transfer-and-extrapolation.txt)

[Corpus index](../index.txt)