Abdelrahman Zayed
@abdelzayed1
Ph.D. candidate at @Mila_Quebec working on fairness in NLP. Former intern at Microsoft Research.
ID: 1759290583821037569
https://abdelrahmanzayed.github.io/ 18-02-2024 18:56:03
15 Tweet
384 Followers
340 Following
Our recent AAAI paper shows that certain attention heads in transformers are responsible for bias and pruning them improves fairness! In collaboration with Goncalo Mordido, Samira Shabanian , Ioana Baldini, and Sarath Chandar Paper π°: arxiv.org/pdf/2312.15398β¦