A Comparative Study of Quality Evaluation Methods for Text Summarization

TL;DR

This paper introduces a new LLM-based method for evaluating text summarization, demonstrating it aligns more closely with human judgment than traditional automatic metrics across patent datasets.

Contribution

The paper presents a novel LLM-based evaluation approach and provides a comprehensive comparison with existing metrics and human assessments.

Findings

LLM evaluation aligns closely with human judgment

Traditional metrics like ROUGE-2 and BERTScore lack consistency

Proposed framework improves automatic evaluation of summarization

Abstract

Evaluating text summarization has been a challenging task in natural language processing (NLP). Automatic metrics which heavily rely on reference summaries are not suitable in many situations, while human evaluation is time-consuming and labor-intensive. To bridge this gap, this paper proposes a novel method based on large language models (LLMs) for evaluating text summarization. We also conducts a comparative study on eight automatic metrics, human evaluation, and our proposed LLM-based method. Seven different types of state-of-the-art (SOTA) summarization models were evaluated. We perform extensive experiments and analysis on datasets with patent documents. Our results show that LLMs evaluation aligns closely with human evaluation, while widely-used automatic metrics such as ROUGE-2, BERTScore, and SummaC do not and also lack consistency. Based on the empirical comparison, we propose a LLM-powered framework for automatically evaluating and improving text summarization, which is beneficial and could attract wide attention among the community.