Extractive Summarization via ChatGPT for Faithful Summary Generation
Submission Type: Regular Short Paper
Submission Track: Summarization
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: summarization, large language model, faithfulness
TL;DR: This paper explores ChatGPT for extractive summarization and propose an extract-then-generate pipeline for faithful summary generation.
Abstract: Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent introduction of large language models has attracted significant interest in the NLP community due to its remarkable performance on a wide range of downstream tasks. This paper first presents a thorough evaluation of ChatGPT's performance on extractive summarization and compares it with traditional fine-tuning methods on various benchmark datasets. Our experimental analysis reveals that ChatGPT exhibits inferior extractive summarization performance in terms of ROUGE scores compared to existing supervised systems, while achieving higher performance based on LLM-based evaluation metrics. In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance. Furthermore, we find that applying an extract-then-generate pipeline with ChatGPT yields significant performance improvements over abstractive baselines in terms of summary faithfulness. These observations highlight potential directions for enhancing ChatGPT's capabilities in faithful summarization using two-stage approaches.
Submission Number: 440
Loading