Hello and welcome to my page! 👋

I am a research technician and lab manager at the Relational Cognition Lab led by Dr. Anna Leshinskaya at UC Irvine. Currently my research is focused on probing language models from both cognitive and AI safety perspectives, specifically on concepts of morality.

I am interested in understanding the internal reasoning processes of language models using theories from cognitive science, behaviorally studying models in complex social simulations, and the relationships between models and brains. More specifically, I am interested in questions like:

• Can we find evidence that language models have the mechanistic capability to combine concepts (compositionality), organize them in a concept space (representational geometry), and programmatically follow rules inferred from them (emergent symbolic structure)? Can we bake these cognitive constructs into models by way of novel training methods or architectural augmentation? [1] [2] [3]

• If language models are put into simulated societies and subjected to economic, social, or ethical pressures, do they navigate the tradeoffs in human-like ways? Can our insights from these value-laden simulations help us catch realistic safety risks before deployment? [4] [5]

• Can encoding models help us build towards a map of functional organization for a language model, analogous to what we currently have for the brain? If we lesion model components based on the mapping between activations and brain regions, do we see the same kind of breakdown patterns as brain lesion studies? [6] [7]

*These questions are broad on purpose — I find all of these areas genuinely exciting and hope to specialize my future work on any one of these threads!*

Prior to this, I was a master’s student at Georgia Tech CS and a member of Language, Intelligence, and Thought (LIT) Lab led by Dr. Anya Ivanova. I was first introduced to neuroAI at Georgia Tech, specifically by a few amazing Psych faculty (Dr. S. Varma, Dr. R. Murty and, of course, Dr. A. Ivanova).

I completed my undergraduate education at UIUC in the CS + Philosophy program, where I took special interest in symbolic logic and ethics.

News

• (4/2026) My second paper “RBCorr: Response Bias Correction in Language Models”, authored with Dr. A. Ivanova, is accepted to the ACL 2026 GEM Workshop! We developed our previous work into a more adaptable method with more comprehensive testing, metrics, and comparisons!
• (4/2025) My first paper (authored with Dr. A. Ivanova), “Estimating and Correcting Yes-No Bias in LMs”, is accepted to the CogSci 2025 conference! I’ll be presenting it there, come and chat!