Abstract
Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard datasets. While these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between their generated summaries and human summarization preferences. This discrepancy is likely due to the low quality of fine-tuning datasets and the limited availability of high-quality human-annotated data that reflect true human preference. To address this challenge, we introduce a novel human summarization preference alignment framework AlignSum. This framework consists of three parts: Firstly, we construct a Data Pymarid with extractive, abstractive, and human-annotated summary data. Secondly, we conduct the Gaussian Resampling to remove summaries with extreme lengths. Finally, we implement the two-stage hierarchical fine-tuning with Data Pymarid after Gaussian Resampling. We apply AlignSum to PLMs on the human-annotated CNN/DailyMail and BBC XSum datasets. Experiments show that with AlignSum, PLMs like BART-Large surpass 175B GPT-3 in both automatic and human evaluations. This demonstrates that AlignSum significantly enhances the alignment of language models with human summarization preferences.- Anthology ID:
- 2024.findings-emnlp.498
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8506–8522
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.498
- DOI:
- 10.18653/v1/2024.findings-emnlp.498
- Cite (ACL):
- Yang Han, Yiming Wang, Rui Wang, Lu Chen, and Kai Yu. 2024. AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8506–8522, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference (Han et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/landing_page/2024.findings-emnlp.498.pdf