SummIt: Iterative Text Summarization via ChatGPT

TL;DR

SummIt introduces an iterative summarization framework using ChatGPT that refines summaries through self-evaluation and feedback, improving faithfulness and controllability over traditional one-shot methods.

Contribution

The paper presents a novel iterative summarization approach with feedback mechanisms and explores knowledge integration to enhance summary quality.

Findings

Improved summary faithfulness and relevance.

Effective iterative refinement demonstrated on benchmark datasets.

Identified over-correction as a potential issue.

Abstract

Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step. However, the one-shot summarization setting is sometimes inadequate, as the generated summary may contain hallucinations or overlook essential details related to the reader's interests. This paper addresses this limitation by proposing SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback, resembling humans' iterative process when drafting and revising summaries. Furthermore, we explore the potential benefits of integrating knowledge and topic extractors into the framework to enhance summary faithfulness and controllability. We automatically evaluate the performance of our framework on three benchmark summarization datasets. We also conduct a human evaluation to validate the effectiveness of the iterative refinements and identify a potential issue of over-correction.