https://taxonomy.eticas.ai/risk/system-explainability
Maturity: emerging
Stakeholders misinterpret or misunderstand the intended purpose or use of an AI system based on its outputs, due to insufficient explanation of how outputs are produced.
This subcategory is emerging. It has not yet been validated through established assessment methods.
System type: ADM and LLM systems
Lifecycle stages: Post Processing
| Framework | Reference |
|---|---|
| NIST AI Risk Management Framework (AI 100-1) | Explainable & Interpretable |
| Framework | Reference |
|---|---|
| W3C Data Privacy Vocabulary — AI Extension | Explainability Risk |
| IBM AI Risk Atlas | Output → Explainability → Unexplainable output |
Source: HRA project taxonomy