Comment on ChatGPT Has Liberal Bias, Say Researchers

<- View Parent
Sekoia@lemmy.blahaj.zone ⁨1⁩ ⁨year⁩ ago

Mhm, but with the way LLMs work, it’s not possible to actually remove bias since it’s baked into the training data. Any adjustment towards “neutral” would be biased by what the adjuster considers neutral.

source
Sort:hotnewtop