Nouha Dziri
I’m a research scientist at Allen Institute for AI (AI2) working with Yejin Choi. Currently, I co-lead the safety and post-training effort at Ai2 to build (OLMo): a highly capable and truly open LLM to advance AI.
Besides this, I work on understanding the limits of Transformers and their inner workings. Check out “Faith and Fate” to learn about the limits of Transformers on reasoning tasks. I also work on studying alignment in LLMs; checkout “Roadmap to Pluralistic Alignment”, “Finegrained RLHF”, and “RewardBench” the first evaluation tool for reward models..
My work has been featured in TechCrunch, LeMonde, The Economist, Science News and QuantaMagazine.
I was 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
| Jul 2025 | Invited lecture about LLM reasoning at the Armenian LLM Summer School 2025  |
|---|---|
| Jul 2025 | Invited talk at the Apple Reasoning and Planning Workshop in Cupertino. |
| Jul 2025 | Invited talk & panel at the Data in Generative Models Workshop at ICML 2025  |
| Jul 2025 | Invited talk & panel at the Computer Use Agents Workshop at ICML 2025 |
| Jul 2025 | Invited talk & panel at the Cross Future AI & Technology Summit in Vancouver |
| Jul 2025 |  1 poster SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behaviorat ICML 2025 |
| Jun 2025 |  Check out our new work “OMEGA: Can LLMs Reason Outside the Box in Math?” |
| May 2025 | Invited talk and panel at the International Symposium on Trustworthy Foundation Models (MBZUAI) |
| May 2025 | Our paper Rel-A.I received the Best Paper Runner Up award at NAACL 2025 |
| Apr 2025 | 1 oral and 2 posters in ICLR 2025 Singapore |
| Feb 2025 |  Guest lecture “Red-Teaming and Safeguarding Language Models: Current Practices, Challenges, and Future Directions” at Carnegie Mellon University (CMU) |
| Feb 2025 | Honored to have been part of the Paris AI Action Summit   |