Objective Metrics for Evaluating Large Language Models Using External Data Sources

Abstract

Evaluating the performance of Large Language Models (LLMs) is a critical yet challenging task, particularly when aiming to avoid subjective assessments. This paper proposes a framework for leveraging subjective metrics derived from the class textual materials across different semesters to assess LLM outputs across various tasks. By utilizing well-defined benchmarks, factual datasets, and structured evaluation pipelines, the approach ensures consistent, reproducible, and bias-minimized measurements. The framework emphasizes automation and transparency in scoring, reducing reliance on human interpretation while ensuring alignment with real-world applications. This method addresses the limitations of subjective evaluation methods, providing a scalable solution for performance assessment in educational, scientific, and other high-stakes domains.

This version of the paper is lightly revised from the EDM 2025 proceedings for the sake of clarity