Bias: Difference between revisions

From Civitai Wiki
Jump to navigation Jump to search
No edit summary
mNo edit summary
 
Line 1: Line 1:
In [[Large language model|Large Language Models]], errors resulting from training data; stereotypes, attributing certain characteristics to races or groups of people, etc.
In [[Large Language Model|Large Language Models]], errors resulting from training data; stereotypes, attributing certain characteristics to races or groups of people, etc.


Bias can cause models to generate offensive and harmful content.
Bias can cause models to generate offensive and harmful content.

Latest revision as of 14:25, 11 April 2024

In Large Language Models, errors resulting from training data; stereotypes, attributing certain characteristics to races or groups of people, etc.

Bias can cause models to generate offensive and harmful content.