What is the MIT AI Risk Repository?

A living database of AI risks extracted from 74 frameworks, taxonomies and papers, classified by a causal taxonomy (entity, intent, timing) and a domain taxonomy (7 domains, 24 subdomains). Published by the MIT AI Risk Initiative under CC BY 4.0.

Can I download the filtered risk list?

Yes. Apply filters and use Export CSV or Export JSON; the file carries the source, licence and citation so it can be reused with attribution.

MIT AI Risk Repository

Browse AI risks

Name: MIT AI Risk Repository: AI Risk Database (browseable copy)
Creator: MIT AI Risk Initiative
License: https://creativecommons.org/licenses/by/4.0/

5 risk entries extracted from 74 frameworks, coded by domain, subdomain, causal entity, intent and timing. Filter, then export the current selection with its licence and citation attached.

Export CSV Export JSON

5 entries

30.01.03 · Risk Sub-Category

Reliability

Inconsistency

models could fail to provide the same and consistent answers to different users, to the same user but in different sessions, and even in chats within the sessions of the same conversation

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

Domain 7 7.3 AI Unintentional Post-deployment
30.05.02 · Risk Sub-Category

Explainability & Reasoning

Limited Logical Reasoning

LLMs can provide seemingly sensible but ultimately incorrect or invalid justifications when answering questions

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

Domain 7 7.3 AI Unintentional Post-deployment
30.05.03 · Risk Sub-Category

Explainability & Reasoning

Limited Causal Reasoning

Causal reasoning makes inferences about the relationships between events or states of the world, mostly by identifying cause-effect relationships

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

Domain 7 7.3 AI Unintentional Post-deployment
30.06.02 · Risk Sub-Category

Social Norm

Unawareness of Emotions

when a certain vulnerable group of users asks for supporting information, the answers should be informative but at the same time sympathetic and sensitive to users’ reactions

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

Domain 7 7.3 AI Unintentional Post-deployment
30.07.00 · Risk Category

Robustness

Resilience against adversarial attacks and distribution shift

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

Domain 7 7.3 AI Other Other

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.