MIT AI Risk Repository · Risk Sub-Category · 30.02.05

Mental Health Issues

Category: Safety

Open the MIT Risk Navigator All entries from Liu2024

On this page 3 sections

Description

unhealthy interactions with Internet discussions can reinforce users’ mental issues

From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: —
Subdomain: —
Causal entity: Not coded
Intent: Not coded
Timing: Not coded

Other entries from Liu2024

Reliability Risk Category · 3.1
Reliability Additional evidence
Misinformation Risk Sub-Category · 3.1
Hallucination Risk Sub-Category · 3.1
Hallucination Additional evidence
Inconsistency Risk Sub-Category · 7.3
Miscalibration Risk Sub-Category · 3.1
Sychopancy Risk Sub-Category · 3.1
Sychopancy Additional evidence
Sychopancy Additional evidence
Safety Risk Category · 1.2
Violence Risk Sub-Category · 1.2