Large Language Models (LLMs) have revolutionized natural language understanding and generation, driving scientific research forward by assisting in all steps of the scientific process, ranging from identifying research gaps to accelerating complex data analysis. In our interdisciplinary research, we explore the diverse applications of LLMs across various scientific domains, from meta-analyses in the science of science to practical implementations in applied fields.
Papers
PRESENTATIONS
Memorization vs. Reasoning: What the vec happens inside LLMs (when solving math questions)?
Presented at the Junior Colloquium UCL on November 27, 2024.