The "black box" nature of GenAI models makes it difficult or impossible to understand the specific reasoning behind a given output. This opacity makes it challenging to diagnose failures, detect hidden biases, and meet regulatory requirements for decision transparency.
AI/ML / Gen AI / Threats / DEV
Lack of Explainability
CCC.GenAI.TH09
Related Capabilities
| ID | Title | Description |
|---|---|---|
| CCC.GenAI.CP21 | Generate Content | Ability to generate a response given a foundation model, parameter values, and a prompt. |
Related Controls
| ID | Title | Description |
|---|---|---|
| CCC.GenAI.CN05 | Citations and Source Traceability | Require the GenAI system to provide citations or direct links back to the source documents used to generate a response, in to enhance the transparency, trustworthiness, and verifiability of AI-generated content. |
External Mappings
| Framework | ID | Remarks |
|---|---|---|
| FINOS-AIGF | AIR-OP-017 | Lack of Explainability |
| FINOS-AIGF | AIR-RC-022 | Regulatory Compliance and Oversight |
| MITRE-ATLAS | AML.T0062.000 | LLM Trusted Output Components Manipulation: Citations |