Jude Fernandes

still trying to make LLMs safer and fairer

[Eric Michael Smith @ericsmithnyc]

Our paper on robust bias evaluation of generative LLMs has been accepted to EMNLP 2023! https://t.co/9KLr86yR6b Thanks to co-authors @davides_io @ellenxtan0 @sagharh @megnung @zycalice @_juderoque Jane Dwivedi-Yu @elepre17 @adinamwilliams

1/2

[Louis Martin @louismrt]

Today at Meta we’re releasing Llama 2, the next generation of our open source LLM available for research and commercial use.
https://t.co/xygo3C5BZY

I am proud to have led the safety effort behind Llama 2. The dedication of the team was key to making our model safer. 🦙
1/n

[Jude Fernandes @_juderoque]

Really grateful to have had the opportunity to work on this project. Fairness has been an issue close to my heart and I believe our work on demographic perturbations for fairer NLP is a big step in the right direction.

[Adina Williams @adinamwilliams]

We’re happy to announce our new preprint on perturbation augmentation for fairer NLP! We trained a seq2seq control-gen model to “perturb” demographic references. We use it to pretrain & finetune LMs that are fairer, without sacrificing accuracy. We measure fairness with it too 🧵