tst123@lemmy.world to Technology@lemmy.worldEnglish · 2 years agoChatGPT Has Liberal Bias, Say Researcherswww.forbes.comexternal-linkmessage-square29fedilinkarrow-up120arrow-down138
arrow-up1-18arrow-down1external-linkChatGPT Has Liberal Bias, Say Researcherswww.forbes.comtst123@lemmy.world to Technology@lemmy.worldEnglish · 2 years agomessage-square29fedilink
minus-squareSekoia@lemmy.blahaj.zonelinkfedilinkEnglisharrow-up6arrow-down1·2 years agoMhm, 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.
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.