Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs

Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon, Ryan A. Rossi, Trung Bui


Abstract
Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite significant advancement achieved in extractive summarization by Large Language Models (LLMs), these summaries frequently exhibit incoherence. An important aspect of the coherent summary is its readability for intended users. Although there have been many datasets and benchmarks proposed for creating coherent extractive summaries, none of them currently incorporate user intent to improve coherence in extractive summarization. Motivated by this, we propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback, offering valuable insights into how to improve coherence in extractive summaries. We utilize this dataset for aligning LLMs through supervised fine-tuning with natural language human feedback to enhance the coherence of their generated summaries. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (~10% Rouge-L) in terms of producing coherent summaries. We further utilize human feedback to benchmark results over instruction-tuned models such as FLAN-T5 which resulted in several interesting findings.
Anthology ID:
2024.emnlp-main.1106
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19810–19820
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1106
DOI:
10.18653/v1/2024.emnlp-main.1106
Bibkey:
Cite (ACL):
Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon, Ryan A. Rossi, and Trung Bui. 2024. Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19810–19820, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs (Parmar et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1106.pdf