BackSituational awareness

This page is still being polished. If you have thoughts, please share them via the feedback form.

Data on this page is preliminary and may change. Please do not share or cite these figures publicly.

Situational awareness

Gipiskis (2024)|LLM classified

Mitigation Taxonomy

99Other

Cannot be confidently classified due to insufficient information, excessive vagueness, or ambiguity.

LLM Classification Details

Reasoning

Insufficient information: "Situational awareness" lacks concrete mechanism details for classification.

Code: 99.9Version: v0.6Classified: Feb 6, 2026

Part of

Agency

Sub-mitigations (1)

Benchmarks for Situational Awareness

A model is situationally aware if it internally represents that it is a machine learning model and if it can accurately infer or act on model-relevant facts - e.g., if it is currently in training, testing, evaluation or deployment, or the desired outcome of an evaluation. Some benchmarks exist for situational awareness of AI models, which test whether the AI models can classify stereotypical inputs from training, testing, evaluation and deployment as such, and whether the AI model can use this information correctly to take actions in the world [25, 111].

3.2.1 Benchmarks & Evaluation

Lifecycle:Other (outside lifecycle)Actor:DeveloperAIRM:Measure

Other mitigations from Gipiskis (2024) (112)

Model development

2.4 Engineering & Development

Lifecycle:Build and Use ModelActor:DeveloperAIRM:Unable to classify

Model development > Data-related

1.1 Model

Lifecycle:Collect and Process DataActor:Unable to classifyAIRM:Unable to classify

Model evaluations

2.2.2 Testing & Evaluation

Lifecycle:Verify and ValidateActor:DeveloperAIRM:Measure

Model evaluations > General evaluations

2.2.2 Testing & Evaluation

Lifecycle:Verify and ValidateActor:DeveloperAIRM:Measure

Model evaluations > Benchmarking

3.2.1 Benchmarks & Evaluation

Lifecycle:Other (outside lifecycle)Actor:DeveloperAIRM:Measure

Model evaluations > Red teaming

2.2.2 Testing & Evaluation

Lifecycle:Verify and ValidateActor:DeveloperAIRM:Measure

View all 112 mitigations from this source →

Source Document

Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems

Gipiškis, Rokas; San Joaquin, Ayrton; Chin, Ze Shen; Regenfuß, Adrian; Gil, Ariel; Holtman, Koen (2024)

Organizations and governments that develop, deploy, use, and govern AI must coordinate on effective risk mitigation. However, the landscape of AI risk mitigation frameworks is fragmented, uses inconsistent terminology, and has gaps in coverage. This paper introduces a preliminary AI Risk Mitigation Taxonomy to organize AI risk mitigations and provide a common frame of reference. The Taxonomy was developed through a rapid evidence scan of 13 AI risk mitigation frameworks published between 2023-2025, which were extracted into a living database of 831 distinct AI risk mitigations.

View source DOI: 10.48550/arXiv.2410.23472

Classification

AI Lifecycle Stage

Unable to classify

Could not be classified to a specific lifecycle stage

Responsible Actor

Developer

Entity that creates, trains, or modifies the AI system

NIST AI RMF Function

Unable to classify

Could not be classified to a specific AIRM function

Risk Domains

Primary

7.2 AI possessing dangerous capabilities

Other

7.1 AI pursuing its own goals in conflict with human goals or values