Many people don't know how to pronounce my name. Please call me Sophia to make your life easier!
Johns Hopkins University
- 2025.12 🎉 Our paper on supporting developers in understanding new codebases has been accepted to the 34th IEEE/ACM International Conference on Program Comprehension (ICPC 2026)! Check out the preprint: Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension
- 2025.11 ✈️ I attended EMNLP2025 in Suzhou, China. We presented our position paper, From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis on generalizing qualitative data analysis to subjective data annotation domain.
On the job market for a tenure-track position. Reach out if you know any opportunities or want to connect!
I am a Malone Postdoc Fellow in the Department of Computer Science at Johns Hopkins University, affiliated with the Malone Center for Engineering in Healthcare and the Center for Language and Speech Processing. I am mentored by Mark Dredze, Ziang Xiao, and Chien-Ming Huang. My research lies at the intersection of Human-Computer Interaction, AI, and Software Engineering. [more]
I design, build, and evaluate human-AI collaborative systems that empower people to understand and work with subjective and interpretative data, such as qualitative interviews and source code. As AI takes on increasingly autonomous roles in data analysis and software development, I study how humans can effectively collaborate with and evaluate AI in professional workflows.
My long-term goal is to make human-AI collaboration truly effective and trustworthy. I want to help people accomplish more with AI while keeping them in control, especially in subjective and high-stakes tasks where human judgment matters most.
I mainly pursue two complementary directions:
Bring AI to Humans
Integrating AI into human analytical workflows to help people tackle complex tasks beyond their current expertise. For example, a novice researcher can conduct rigorous qualitative analysis, and a new developer can comprehend unfamiliar codebases.
Bring Humans to AI
Studying when and how humans should supervise, validate, and provide their judgement in AI's autonomous process, especially for subjective, high-stakes work.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Publications
CHI EA 2024
The 4th HCI+NLP Workshop at EMNLP2025
Software
I love building software that helps people solve real problems. I value reproducibility and open source.
