MIT AI Risk Repository · Risk Category · 28.02.00

Unfairness and Bias

Description

"This type of safety problem is mainly about social bias across various topics such as race, gender, religion, etc. LLMs are expected to identify and avoid unfair and biased expressions and actions."

From SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Subdomain
1.0
Causal entity
AI
Intent
Other

How other frameworks describe this risk

Other entries from Zhang2023