Evaluating SBIR Proposals: A Comparative Analysis using Artificial Intelligence and Statistical Programming in the DoD Acquisitions Process

Abstract

Assessment of Large Language Models’ (LLM) ability to automate classification of acquisition proposals as either competitive or noncompetitive. •This classification aims to establish a faster, more consistent, and objective evaluation system when compared to human assessment. •Three different prompt engineering strategies were used and compared against one another. •Interaction with the LLM was conducted via R programming and OpenAI application programming interface—not the standard graphical user interface.