Meet the Fellow: Saadia Gabriel
This entree is a part of our Meet the Fellow blog series, which introduces and highlights Faculty Fellows who have recently joined CDS
Meet CDS Faculty Fellow Saadia Gabriel, who will be joining us this fall. Gabriel received her PhD from the Paul G. Allen School of Computer Science & Engineering at the University of Washington. She is currently a CSAIL Postdoctoral Fellow at MIT, and in July 2024, she’ll become an Assistant Professor at the Samueli School of Engineering at UCLA.
Gabriel works on the evaluation of accuracy and intent in human-written text. She is interested in “designing generalizable end-to-end modeling frameworks based upon objectives that are directly aligned with the underlying motivations of a task.” She is particularly enthusiastic about exploring two aspects of machine reasoning: social commonsense reasoning, and fairness in NLP.
Gabriel stands out not only for her academic prowess but also her drive to leverage technology for social good. She published papers at ACL 2022 on mitigating discriminatory decision-making by hate speech classifiers and predicting societal impact of news claims. Last fall, Gabriel’s paper “NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?” on testing the robustness of natural language inference (NLI) and hate speech classifiers with generated adversaries was accepted to EMNLP Findings. She also has a paper in submission called “Can Machines Learn Morality? The Delphi Experiment,” which describes a framework trained to reason about “descriptive ethical judgments,” i.e. evaluating the morality of, for example, “helping a friend spread fake news.” She has also recently been invited to give talks at UCLA, MIT and Princeton, and, in June, gave a talk at Spotify NYC. She will be the Tutorial Co-Chair for NeurIPS 2023.
“At NYU I’d love to collaborate broadly with the amazing researchers there to bridge the gap between machine cognition and the social complexities of communities impacted by AI,” said Gabriel. “My main goal is to address how we can safely and ethically deploy natural language processing (NLP) systems that serve all users equitably.”
Gabriel has interned at SRI, in the Mosaic group at the Allen Institute for AI (AI2), and Microsoft Research Lab (MSR). Before her PhD, Gabriel earned a Master’s in Computer Science & Engineering from the University of Washington, and a BA in Computer Science & Mathematics from Mount Holyoke College.
To view all our current faculty fellows, please visit the CDS Faculty Fellow page on our website.
By Stephen Thomas
