A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations

TL;DR

This paper systematically reviews the challenges and limitations in evaluating Large Language Models, highlighting inconsistencies and proposing recommendations for more reliable and reproducible assessments.

Contribution

It provides a comprehensive analysis of evaluation challenges and offers guidelines to improve the reliability and consistency of LLM assessments.

Findings

Identification of key challenges in LLM evaluation

Analysis of factors causing evaluation inconsistencies

Recommendations for standardized evaluation practices

Abstract

Large Language Models (LLMs) have recently gained significant attention due to their remarkable capabilities in performing diverse tasks across various domains. However, a thorough evaluation of these models is crucial before deploying them in real-world applications to ensure they produce reliable performance. Despite the well-established importance of evaluating LLMs in the community, the complexity of the evaluation process has led to varied evaluation setups, causing inconsistencies in findings and interpretations. To address this, we systematically review the primary challenges and limitations causing these inconsistencies and unreliable evaluations in various steps of LLM evaluation. Based on our critical review, we present our perspectives and recommendations to ensure LLM evaluations are reproducible, reliable, and robust.