MIT AI Risk Repository · Risk Sub-Category · 02.01.01
Bias
Category: Harmful Content
Description
"The training datasets of LLMs may contain biased information that leads LLMs to generate outputs with social biases"
From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Causal entity
- AI
- Intent
- Unintentional
- Timing
- Other
Subdomain definition: Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and representation of those groups.
Real-world incidents in this subdomain
- DOGE Reportedly Relied on Unvetted ChatGPT Outputs in Canceling National Endowment for the Humanities Grants
- Sora Video Generator Has Reportedly Been Creating Biased Human Representations Across Race, Gender, and Disability
- Meta AI Characters Allegedly Exhibited Racism, Fabricated Identities, and Exploited User Trust
- Alleged AI-Generated Photo Alteration Leads to Inappropriate Modifications in Speaker's Conference Picture
- Algorithmic Bias in French Welfare System Allegedly Discriminates Against Marginalized Groups
- Department for Work and Pensions (DWP) AI Systems Allegedly Discriminate Against Single Mothers