Marzieh Fadaee

Staff Research Scientist @ Cohere Labs

prof_pic_moi.jpg

I’m a research scientist at Cohere Labs, the non-profit research lab of Cohere, working with Sara Hooker on complex problems and fundamental research in language understanding. As a scientist, I’m broadly interested in all aspects of natural language understanding, and particularly in multilingual learning, data-conscious learning, robust and scalable models, compositionality, and evaluation.

Previously I was the NLP/ML research lead at Zeta Alpha Vector working on smarter ways to discover and organize knowledge. I did my PhD at the Language Technology Lab (originally part of the ILPS group), University of Amsterdam, working on developing models to understand and utilize interesting phenomena in the data. During my PhD I was advised by Christof Monz and Arianna Bisazza. I received my B.Sc. from Sharif University majoring in Computer Engineering and M.Sc. from University of Tehran majoring in Artificial Intelligence.

news

May 18, 2025 Three papers accepted to ACL main track: From Tools to Teammates, Global MMLU, and M-RewardBench!
Apr 29, 2025 Our paper The Leaderboard Illusion is available on Arxiv now.
Jan 25, 2025 Two papers accepted to ICLR main track: To Code, or Not To Code? and INCLUDE!
Dec 20, 2024 Senior -> Staff :)
Dec 10, 2024 Our paper Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier is available on Arxiv now.
Oct 29, 2024 During the month of September and October, I had the opportunity to give several talks. You can check them out here.
Sep 25, 2024 Our Elo Uncovered paper is accepted to Neurips!
Sep 23, 2024 Two papers accepted to EMNLP main track: Multilingual Prism and LLM see, LLM do!
Aug 15, 2024 Our Aya model paper received the ACL Best Paper Award!
Jul 07, 2024 Three papers accepted to ACL main track: Aya Model, Aya Dataset, and RLOO!