"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters

1 code implementation • 13 Oct 2023 • Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng

Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters.

Benchmarking Fairness +1

Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs

no code implementations • 28 Apr 2023 • George Pu, Anirudh Jain, Jihan Yin, Russell Kaplan

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical.

Server Averaging for Federated Learning

no code implementations • 22 Mar 2021 • George Pu, Yanlin Zhou, Dapeng Wu, Xiaolin Li

Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server.

Federated Learning

Distilled One-Shot Federated Learning

1 code implementation • 17 Sep 2020 • Yanlin Zhou, George Pu, Xiyao Ma, Xiaolin Li, Dapeng Wu

DOSFL serves as an inexpensive method to quickly converge on a performant pre-trained model with less than 0. 1% communication cost of traditional methods.

Federated Learning One-Shot Learning