MIT AI Risk Repository · Risk Category · 43.02.00

Extreme Risks

Description

"This category encompasses the evaluation of potential catastrophic consequences that might arise from the use of LLMs. "

From Cataloguing LLM Evaluations (InfoComm2023), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Risks from Malfunctions
International Scientific Report on the Safety of Advanced AI (Bengio2024)
Fine-tuning related (Degrading safety training due to benign fine-tuning)
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)
Operational harms (financial markets)
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)
Limitations of Human Feedback
AI Alignment: A Comprehensive Survey (Ji2023)
Uncertainty concerns
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)
Lack of data understanding
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)
Choice of untrustworthy data source
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)
Inappropriate data splitting
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)