Chi Zhang

Chi (Charlie) Zhang is a master’s student in Statistics at Columbia University in the Advanced Machine Learning track. His academic training focuses on statistical learning and applied machine learning, with an emphasis on rigorous model evaluation and methodological reliability in real-world text and social science data. He is particularly interested in the use of large language models for qualitative research, including topic modeling and automated coding of text data. His prior work includes developing retrieval-augmented generation (RAG)–based systems for document analysis and conducting empirical evaluations of machine learning models under noisy data conditions.

As part of the AI4SGS program, Chi looks forward to contributing to the ENVIO research team by supporting rigorous comparisons between LLM-based coding and human annotation, with the goal of improving analytic reliability and research workflow efficiency in social science and public health research.