Thomas Randall @ Clemson University

Poster for OMNI Internship @ Oak Ridge National Laboratory, 2024



Bar plots showing LLM capability to perform addition and modulus operations based on several factors.

Quick Links

Media

Publication Details

Appears in DOE Cybersecurity and Technology Innovation 2024 by authors: Thomas Randall, Rong Ge, and Prasanna Balaprakash

Abstract

Large Language Models (LLMs) capture a certain amount of world knowledge spanning many general and technical topics, including programming and performance. Without fine-tuning, the use of In-Context Learning (ICL) can specialize LLM outputs to perform complex tasks. In this work, we seek to demonstrate the regressive capabilities of LLMs in a performance modeling capacity. We find initial evidence that may limit LLM utility even after fine-tuning.