Question-Answering Approach to Evaluating Legal Summaries

TL;DR

This paper introduces a GPT-4 based question-answering framework for evaluating legal summaries, focusing on argumentative structure rather than lexical overlap, and shows promising correlation with human judgments.

Contribution

It presents a novel GPT-4 driven evaluation method for legal summaries that considers argumentative content, improving upon traditional lexical overlap metrics.

Findings

GPT-4-based evaluation correlates well with human grading

The method effectively captures legal summary quality

It offers a new approach for legal summarization assessment

Abstract

Traditional evaluation metrics like ROUGE compare lexical overlap between the reference and generated summaries without taking argumentative structure into account, which is important for legal summaries. In this paper, we propose a novel legal summarization evaluation framework that utilizes GPT-4 to generate a set of question-answer pairs that cover main points and information in the reference summary. GPT-4 is then used to generate answers based on the generated summary for the questions from the reference summary. Finally, GPT-4 grades the answers from the reference summary and the generated summary. We examined the correlation between GPT-4 grading with human grading. The results suggest that this question-answering approach with GPT-4 can be a useful tool for gauging the quality of the summary.