Georgia Liu

I use LLMs to turn interviews, verbatim responses and quotes into causal graphs, and I build benchmarks that measure how closely those graphs match expert-built ones. I’m the founder of Causena, where we turn interviews, debriefs and reports into source-cited causal graphs that show what drives real-world outcomes. Before Causena, I was a Postdoctoral Research Fellow at Harvard Medical School / Massachusetts General Hospital in the MJ Lab, where I built a framework for comparing causal graphs on both meaning and structure, and used it to evaluate 2,000 LLM-generated graphs. Before that, I was an AI Resident at Google X, using LLMs to automate causal modeling. I did my PhD in Industrial and Systems Engineering with Dr. Konstantinos Triantis in Virginia Tech’s Systems Performance Lab, and an MS in Computer Science focused on AI and machine learning.

I’m always happy to talk about LLM evaluation, information extraction, and causal AI for messy qualitative data.