Nouha Dziri

prof_pic.jpg

I’m a research scientist at Allen Institute for AI (AI2) working with Yejin Choi and the Mosaic team. Currently, I lead the safety effort at AI2 to align OLMO models with ethical principles while preserving their reasoning capabilities. Besides safety, I work on

  • Science of LMs: Understanding the limits of Transformers and their inner workings. Check out “Faith and Fate” to learn about the limits of Transformers on reasoning tasks.

In the past, I earned my PhD from the University of Alberta and the Alberta Machine Intelligence Institute with Osmar Zaiane. I was also fortunate to work with brilliant researchers in the field. I have worked with Siva Reddy at Mila/McGill, with Hannah Rashkin, Tal Linzen, David Reitter, Diyi Yang, and Tom Kwiatkowski at Google Research NYC and have worked with Alessandro Sordoni, and Goeff Gordon at Microsoft Research Montreal.

News

May 2024 Invited Talk “What it can create, it may not understand” Studying the Limits of Transformers” at the University of Cambridge.
Feb 2024 Featured in TechCrunch talking about why LMs perform better when we “motivate” them or ask them “nicely”?
Jan 2024 3 papers accepted at ICLR 2024. 1 Oral and 2 posters. See you in Vienna :musical_score: :musical_note: :musical_note:
Dec 2023 Guest Lecture: “Limits of Generative AI Models and their Societal Implications” for the “Generative AI” course taught by Prof. Adji Bousso at the Princeton University.
Nov 2023 Invited Talk: Presented “Faith and Fate” & “Generative AI Paradox” at LLM evaluation workshop at The Alan Turing Institute.
Nov 2023 Invited Talk: Presented “Faith and Fate” in ILCC CDT/NLP seminar, University of Edinburgh.
Nov 2023 Invited Talk: Presented “Faith and Fate” at SAIL workshop on fundamental limits of LLMs.
Nov 2023 New paper :mega: “The Generative AI Paradox: What It Can Create, It May Not Understand” is out. [Paper]
Oct 2023 New paper :mega: “Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement” is out. (ICLR Oral 2024) [Paper][Code]
Oct 2023 Invited Talk: Presented “Faith and Fate” at the University of Pittisburgh
Oct 2023 2 papers accepted at EMNLP.
Sep 2023 Invited Talk: Presented “Faith and Fate” at the Formal Languages and Neural Networks Seminar [Video]