Question-Answering Approach to Evaluating Legal Summaries
This addresses the need for better evaluation metrics in legal summarization by moving beyond lexical overlap to consider argumentative structure, though it is incremental as it adapts existing AI methods.
The paper tackled the problem of evaluating legal summaries by proposing a question-answering framework using GPT-4 to generate and grade answers, finding it correlates with human grading as a useful tool.
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.