Varsha Rajesh
Research Mentor(s): Geoffrey Siwo
Mentor Department: Learning Health Sciences
Authors: Varsha Rajesh, Geoffrey Siwo
Session: Session 6 (3:00pm – 3:50pm)
Presentation Type: Poster 28
Abstract
Analyzed the performance of three large language models (LLMs), GPT-3.5, Llama 3 (70b), and GPT-4.0, on various bioinformatics tasks provided by the Rosalind platform. The performance of each LLM was compared to human performance on the Rosalind site. Various correlations were found by making plots and performing univariate and bivariate analyses through Python.
