Can Large Language Models Be an Alternative to Human Evaluations?

TL;DR

This paper investigates whether large language models can replace human evaluators in assessing text quality, demonstrating that LLM-based evaluations align with expert judgments and are more stable and reproducible.

Contribution

The study introduces LLM evaluation as a novel method for assessing text quality, showing its consistency with human evaluations across multiple NLP tasks.

Findings

LLM evaluation correlates well with human expert ratings

Results are stable across different task instruction formats

LLMs can reliably evaluate open-ended and adversarial texts

Abstract

Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable, hindering fair comparisons among different natural language processing (NLP) models and algorithms. Recently, large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided. In this paper, we explore if such an ability of the LLMs can be used as an alternative to human evaluation. We present the LLMs with the exact same instructions, samples to be evaluated, and questions used to conduct human evaluation, and then ask the LLMs to generate responses to those questions; we dub this LLM evaluation. We use human evaluation and LLM evaluation to evaluate the texts in two NLP tasks: open-ended story generation and adversarial attacks. We show that the result of LLM evaluation is consistent with the results obtained by expert human evaluation: the texts rated higher by human experts are also rated higher by the LLMs. We also find that the results of LLM evaluation are stable over different formatting of the task instructions and the sampling algorithm used to generate the answer. We are the first to show the potential of using LLMs to assess the quality of texts and discuss the limitations and ethical considerations of LLM evaluation.