@animaanandkumar : We are excited to share our latest work on debiasing large language models, accepted to COLM 25024 We introduce a lightweight, simple pipeline using ChatGPT to generate synthetic data for debiasing open-source LLMs through parameter-efficient fine-tuning. Our method outperforms • TwiCopy

Prof. Anima Anandkumar

@animaanandkumar

+ Follow

Bren Professor @caltech, Time100, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.

ID: 1393424079634395139

linkhttp://tensorlab.cms.caltech.edu/users/anima/ calendar_today15-05-2021 04:32:55

2,2K Tweet

31,31K Followers

2,2K Following

Prof. Anima Anandkumar

@animaanandkumar

8 months ago

We are excited to share our latest work on debiasing large language models, accepted to COLM 2024 We introduce a lightweight, simple pipeline using ChatGPT to generate synthetic data for debiasing open-source LLMs through parameter-efficient fine-tuning. Our method outperforms

thumb_up_off_alt48

chat_bubble_outline1

repeat8

shareShare