Karol 佳嵘 · M.S.Ed. researcher at Johns Hopkins

Generative AI in Education · Learning Technologies · Instructional Design · Educational Equity · Evaluative Judgment.

Johns Hopkins University

Relevant coursework: Social Research; Statistics; Global Education Policy and Analysis; Qualitative Inquiry; Global Trends in Education.

The Ohio State University

Marketing major (GPA 3.85/4.0) · History minor (GPA 3.9/4.0).

Researcher · Multiagent LLM Scaffolding for Simulated Clinical Consultations

• Built and evaluated a multiagent large language model system that distributes patient interaction, tutoring, checklist monitoring, and final feedback across specialized agents to scaffold simulated medical consultations.
• Found that multiagent scaffolding improved overall consultation quality — with gains concentrated in communication, empathic expression, and detailed information gathering — rather than in diagnostic correctness.

Co-author · Hallucination-Aware Learning Research Project

• Co-developed a Hallucination-Aware Learning (HAL) framework for generative AI use in medical education.
• Examined how structured exposure to AI-generated errors may strengthen learners' verification skills, evaluative judgment, and critical engagement.
• Integrated theories of productive failure, cognitive friction, and AI-supported learning design to conceptualize instructional responses to hallucination risks.

Student Assistant · Ride4Refugee Project

• Designed and distributed surveys to investigate transportation barriers and community needs among refugee populations in Columbus.
• Synthesized qualitative and quantitative findings into a report with actionable recommendations for community stakeholders.
• Collaborated with the Central Ohio Transit Authority on solution-oriented planning, gaining experience in community-based research and policy-adjacent program implementation.

"When Discipline Becomes Ambiguous Harm: Rethinking Responsibility in School Responses"

"Who Bears the Cost of Verification? Generative AI, Educational Equity, and Policy Challenges Across Educational Systems"

First-author manuscript

An education-side examination of the emerging educational divide in the age of generative AI — who has access, who learns to use it well, and what schools can do about it. Currently under peer review.

Cum Laude · The Ohio State University.

• Dean's List · 5 semesters
• Allen Family Scholarship

Stata · SPSS · Qualtrics · Survey design · Zotero · Python · C++.

Mandarin Chinese (native) · English (fluent) · Cantonese (conversational) · Korean (basic).