Computer Science PhD student at Stony Brook University
Advisor: Owen Rambow
Email: jmurzaku <at> cs.stonybrook <dot> edu
About me
I'm a 5th year Computer Science PhD candidate at Stony Brook working on belief modeling in text and multimodal contexts. I am advised by Owen Rambow, and work on how to better understand how language models represent, reason about, and generate beliefs in conversation— particularly around mental states, factuality, and common ground.
My work spans computational linguistics and cognitive science, bridging theory-of-mind concepts with modern NLP. I am also interested in how large language models process spontaneous narratives and how we can evaluate or improve their ability to detect hedges, sarcasm, or other subtle markers of speaker intent. This work is a joint and ongoing collaboration with Susan Brennan from the Stony Brook Psychology Department.
Recently, I interned at Adobe working on interactive disambiguation and clarification question generation for enterprise AI assistants. I previously also completed internships at Gap International and Raytheon, focusing on real-world NLP applications such as authorship attribution, topic modeling, and knowledge-grounded dialogue.
Updates
My Adobe internship work on Enhanced Clarification for Interactive Responses (ECLAIR) to appear AAAI 2025 (Demo) and IAAI 2025. Another publication on Synthetic Audio Data accepted to Findings of NAACL 2025.
Interned at the Genius Institute at Gap International as an NLP Engineer. I helped leverage LLMs to detect patterns of genius and built an unsupervised clustering pipeline for genius detection. I was mentored by my amazing father Alex Murzaku (also fulfilling my childhood dream of one day working together with my dad).