Computational cognitive science and AI
I study how people think, decide, and learn by combining cognitive modeling, think-aloud data, and large language models.
Cognitive Modeling Think-Aloud Protocols Human-Centered AI
Computational approaches to cognition, decision-making, and human-centered AI.
I am a Ph.D. student in Psychology at the Georgia Institute of Technology, specializing in computational cognitive science. My work asks how language, behavior, and computational models can reveal the hidden structure of human thought.
My thesis uses large language models to analyze think-aloud data from decision-making and learning tasks. Rather than treating behavior as only button presses or choices, I use participants' verbal reports as a richer window into strategies, beliefs, and latent cognitive processes. I am especially interested in when LLMs can help measure these processes reliably, and where human judgment remains essential.
I also study AI systems through ideas from psychology and neuroscience: how models explore, reason, explain decisions, and interact with people. More broadly, I am interested in AI-assisted scientific discovery that expands, rather than replaces, careful empirical work.
Before Georgia Tech, I earned an M.A. from the University of Arizona and spent three years as a full-time research assistant at Peking University's CBCS. From March to July 2025, I visited Tom Griffiths' CoCoSci Lab at Princeton University as a Visiting Student Research Collaborator.
Selected themes connecting cognitive science, language, behavior, and AI.
The think-aloud protocol asks participants to verbalize their thoughts while they perform psychological tasks. Traditional work has mostly relied on behavioral outputs (often button presses) to infer latent cognitive processes. In many cases, candidate cognitive models are proposed and tested by researchers, which can limit the hypothesis space and introduce bias. By directly analyzing participants' verbal reports, we gain a richer and more direct view of cognition during task performance. However, most prior think-aloud research depends on manual coding by experts, which is labor-intensive, subjective, and difficult to scale.
Recent advances in LLMs make it possible to revisit this classic protocol with stronger computational tools. LLMs can help quantify, interpret, and even predict subsequent behavior from think-aloud language. Our work evaluates when and how these models can be used reliably, with the goal of building a more systematic and scalable framework for studying human thought processes.
Representative publications:
Human thought is central to intelligence, yet it is difficult to define, measure, and model. A core challenge in both cognitive science and AI is to characterize thought processes across tasks, identify shared principles, and generalize those principles to make useful predictions. The difficulty is that thoughts are often implicit, while language is diverse and context-dependent. As a result, verbal reports are informative but still incomplete reflections of internal cognition.
Instead of focusing only on the forward direction (how thoughts generate behavior), this project emphasizes inverse inference: given observed behavior and related measurements, can we reconstruct plausible underlying thoughts? The broader goal is to build a stronger, more general bridge between behavior and cognition. This direction also supports a human-centered understanding of machine reasoning. If the computations of complex systems (e.g., AlphaGo-like models) can be approximated by human-trained explanatory models, we may be able to describe model reasoning in natural language that is useful for teaching, interpretation, and collaboration.
This project began during my Princeton visit and remains an active research direction.
Representative publications:
This project examines AI through concepts from psychology and neuroscience. By comparing strengths and weaknesses of AI and human intelligence, we can design models that are both more capable and more interpretable. Beyond technical performance, I am interested in societal value: systems that support human decision-making, education, and collaboration. I also explore how people can learn from advanced AI models when we build the right frameworks to analyze and communicate their internal computations.
Representative publications:
The human mind is deeply complex. Although thoughts, emotions, and actions are part of everyday experience, formally describing and predicting cognition remains a major scientific challenge. Many cognitive theories are grounded in human intuition and then tested through experiments and computational models. These approaches are powerful, but they can remain constrained by the original hypothesis space.
In the AI era, there is an opportunity to rethink discovery pipelines in cognitive science and psychology. LLMs bring broad knowledge and strong inductive biases, and modern reasoning models can perform at levels that sometimes rival expert intuition. A central question for my work is whether we can build AI-assisted workflows that help discover new behavioral phenomena, generate computational models, and propose testable theories while reducing avoidable human bias. I view this as complementary to, not a replacement for, careful empirical research.
Representative publications:
* Denotes equal contribution, † Denotes Correspondence, Underscore denotes mentee. Use topic filters to navigate.
Essays and notes at the intersection of cognitive science and AI.
How large behavioral datasets and powerful AI models can rapidly improve predictive performance while scientific understanding lags behind — and why data and knowledge bottlenecks matter for the future of cognitive science.
Read postEmail: hanboxie1997@gatech.edu
Address: 750 Ferst Drive, Atlanta, GA 30332