MIT AI Risk Repository · Risk Sub-Category · 62.18.05

Model outputs inconsistent with chain-of-thought reasoning

Category: Model Evaluations (Interpretability/Explainability)

Description

"Chain-of-thought reasoning is sometimes employed to get a better understanding of the model’s output, where it encourages transparent reasoning in text form. However, in some cases, this reasoning is not consistent with the final answer given by the AI model, and as such does not give sufficient transparency [113]."

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

Causal entity
AI

Subdomain definition: Challenges in understanding or explaining the decision-making processes of AI systems, which can lead to mistrust, difficulty in enforcing compliance standards or holding relevant actors accountable for harms, and the inability to identify and correct errors.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from Gipiškis2024