Less is More for Long Document Summary Evaluation by LLMs

Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka


Abstract
Large Language Models (LLMs) have shown promising performance in summary evaluation tasks, yet they face challenges such as high computational costs and the Lost-in-the-Middle problem where important information in the middle of long documents is often overlooked. To address these issues, this paper introduces a novel approach, Extract-then-Evaluate, which involves extracting key sentences from a long source document and then evaluating the summary by prompting LLMs. The results reveal that the proposed method not only significantly reduces evaluation costs but also exhibits a higher correlation with human evaluations. Furthermore, we provide practical recommendations for optimal document length and sentence extraction methods, contributing to the development of cost-effective yet more accurate methods for LLM-based text generation evaluation.
Anthology ID:
2024.eacl-short.29
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
330–343
Language:
URL:
https://aclanthology.org/2024.eacl-short.29
DOI:
Bibkey:
Cite (ACL):
Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, and Estevam Hruschka. 2024. Less is More for Long Document Summary Evaluation by LLMs. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 330–343, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Less is More for Long Document Summary Evaluation by LLMs (Wu et al., EACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eacl-short.29.pdf
Video:
 https://aclanthology.org/2024.eacl-short.29.mp4