Itay Itzhak
I'm interested in
About
I am a PhD student at the Technion, lucky to be advised by Yonatan Belinkov and Gabriel Stanovsky from the Hebrew University in Jerusalem.
My research focuses on analyzing language models to discover their flaws and study human-like biases. I'm particularly interested in decision-making and reasoning that may affect real-world applications.
I have previously worked at Meta AI Research, where I analyzed attention patterns of translation models. I hold an M.Sc. from Tel Aviv University, where I worked with Omer Levy on probing the embeddings matrix of language models, discovering surprising spelling information within tokens.
I am always open to collaborations and enjoy discussing research, language models, and everything in between. Feel free to reach out via email!
Publications
Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
Itay Itzhak, Gabriel Stanovsky, Nir Rosenfeld, Yonatan Belinkov
TACL 2024
[Code]Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Itay Itzhak, Omer Levy
NAACL 2022
[Code] / [Talk]The impact of tumor detection method on genomic and clinical risk and chemotherapy recommendation in early hormone receptor positive breast cancer
Yael Bar, Kfir Bar, Itay Itzhak, Chen Shitrit Niselbaum, N. Dershowitz, E. Shachar, A. Weiss-Meilik, O. Golan, I. Wolf, T. Menes, A. Sonnenblick