Janka Franciska Hamori

Janka Franciska Hamori

Scholar Title

MIT Tang Family FinTech Undergraduate Research and Innovation Scholar

Research Title

Do LLMs Synthesize Technical Information Like Humans?

Cohort

2024–2025

Department

Electrical Engineering and Computer Science

Research Areas
  • AI and Machine Learning
Supervisors

Andrew W. Lo

Antonio Torralba

Mentor

Jillian Ross

Abstract

My project investigates how large language models (LLMs) lose critical technical information during information synthesis, and how these gaps vary across different scientific fields. By categorizing the errors, we identify consistent challenges in handling theoretical foundations and performance evaluation, with computer science showing the most significant decline in accuracy. The findings emphasize fundamental limitations in LLMs’ ability to process and retain critical scientific knowledge, offering a foundation for targeted improvements in AI-assisted scientific analysis.

Quote

I am participating in Super UROP to connect my main interest areas AI, mathematics and finance through high-level research. This is a great opportunity for me to do work in the intersection of my majors Business (15-2) and AI (6-4), while learning more about financial markets, and how to work with LLMs. I am also interested in LLM capability research, particularly how their use in everyday life influences larger systems and drives broader societal changes.

Back to Scholars