Skip to main content

Toxicity

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

Sub-category
Risk Domain

AI that exposes users to harmful, abusive, unsafe or inappropriate content. May involve providing advice or encouraging action. Examples of toxic content include hate speech, violence, extremism, illegal acts, or child sexual abuse material, as well as content that violates community norms such as profanity, inflammatory political speech, or pornography.

language being rude, disrespectful, threatening, or identity-attacking toward certain groups of the user population (culture, race, and gender etc)(p. 25)

Supporting Evidence (1)

1.
in the training dataset of LLMs can contain a non-negligible portion of toxic comments(p. 25)

Part of Social Norm

Other risks from Liu et al. (2024) (34)