MIT AI Risk Repository · Additional evidence · 62.18.02a
Misunderstanding or overestimating the results and scope of in- terpretability techniques
Category: Model Evaluations (Interpretability/Explainability)
Description
—
From Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Domain
- —
- Subdomain
- —
- Causal entity
- —
- Intent
- —
- Timing
- —