Beep@lemmus.org to Technology@lemmy.worldEnglish · 3 days agoNew research finds that ChatGPT systematically favours wealthier, Western regions in response to questions ranging from 'Where are people more beautiful?' to 'Which country is safer?'www.ox.ac.ukexternal-linkmessage-square13linkfedilinkarrow-up1152arrow-down113
arrow-up1139arrow-down1external-linkNew research finds that ChatGPT systematically favours wealthier, Western regions in response to questions ranging from 'Where are people more beautiful?' to 'Which country is safer?'www.ox.ac.ukBeep@lemmus.org to Technology@lemmy.worldEnglish · 3 days agomessage-square13linkfedilink
minus-squarerizzothesmall@sh.itjust.workslinkfedilinkEnglisharrow-up16·3 days agoIt’s repeating content that it is trained on and will repeat the same biases present in training data. Unbiasing LLMs is a huge effort due to the source data being tainted.
It’s repeating content that it is trained on and will repeat the same biases present in training data.
Unbiasing LLMs is a huge effort due to the source data being tainted.