Hello, my name is Sonia.
I care about understanding humans as thinking, feeling, computational machines and using these insights to build artificial intelligence that better serves a diversity of human intelligence. I study how machines act as social partners, and use the tools of computational cognitive science and human-AI interaction to evaluate and improve their behavior. I view scientific research as a creative endeavor, and one vehicle for the thought-forms I hope to project into the world.
I am currently on leave from my PhD in Computer Science at Harvard University. I am grateful to be advised by Tomer Ullman, and to be supported by an NSF Graduate Research Fellowship and Kempner Institute Graduate Fellowship. Previously, I spent time collaborating with researchers at the UK AI Security Institute and Google DeepMind on human-AI complementarity for scalable oversight, was a Predoctoral Young Investigator at the Allen Institute for Artificial Intelligence (AI2) working on personalized descriptions of scientific concepts, and completed my undergraduate studies at Princeton University, where I got my start in computational cognitive science building models of word-color associations in humans to understand synesthesia.
Selected Publications
spotlight talk
Beyond Anthropomorphism: a Spectrum of Interface Metaphors for LLMs
CHI Extended Abstracts (2026)
Cognitive models can reveal interpretable value trade-offs in language models
ICLR (2026)
An earlier iteration of this work appeared as spotlight talks at thePragmatic Reasoning in Language Models workshop @ COLM 2025 andInterpreting Cognition in Deep Learning Models workshop @ NeurIPS 2025
Priors in Time: Missing Inductive Biases for Language Model Interpretability
ICLR (2026)
An earlier iteration of this work appeared at the Interpreting Cognition in Deep Learning Models workshop @ NeurIPS 2025
One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity
NAACL (2025)
Please see Google Scholar for a full list of publications.
Invited talks
Brown University, ANCOR seminar series
Google DeepMind, VOICES team
Annual Meeting of the Society for Neuroeconomics, "AI in Neuroeconomics" panel
If you would like to chat about research, or are a minority student considering graduate school in Psychology or Computer Science, please feel free to reach out to me at soniamurthy [at] g [dot] harvard [dot] edu and I will do my best to respond!