๐Ÿ”AI RiskAtlas
โ† Risk Taxonomy
#14

Lack of explainability

Risk taxonomy

Definition

Challenge of understanding how the Gen AI modelling techniques influence model behaviour and outputs.

Controls & guardrails that address this

6

Grouped by control function, with the AI lifecycle stage(s) to apply each and the other risks it addresses. Filter by control category below.

Control category
Preventive ยท 6
Explainability requirements aligned to regulatory needs

Define explainability requirements at design stage aligned to regulatory obligations and affected user needs.

Lifecycle stage1 โ€“ Use Case Context & Design
Post hoc interpretability techniques

Select model architecture with explainability in mind. Prefer inherently interpretable models where performance requirements permit.

Lifecycle stages1 โ€“ Use Case Context & Design3 โ€“ Onboarding, Build & Review
Chain-of-thought prompting

Design system prompts to elicit step-by-step chain-of-thought reasoning. Validate that reasoning is accurate and not post-hoc.

Lifecycle stage3 โ€“ Onboarding, Build & Review
Counterfactual explanations

Implement counterfactual explanation generation for each AI decision. Validate fidelity before deployment.

Lifecycle stage3 โ€“ Onboarding, Build & Review
Also addressesHallucination
Contextual decision explanations for affected users

Provide contextually appropriate explanations of AI decisions to affected users in the production interface.

Lifecycle stage5 โ€“ Usage, Monitoring & Change
Confidence scoring

Surface confidence indicators alongside AI outputs in production. Update indicators when confidence calibration drifts.

Lifecycle stage5 โ€“ Usage, Monitoring & Change
Open these in the Control Library โ†’

Other risks in Transparency

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning โ€” not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading โ†’ยทBuilt by Shi Yuan โ†—