HonestBait: Forward References for Attractive but Faithful Headline Generation

Chih Yao Chen, Dennis Wu, Lun-Wei Ku


Abstract
Current methods for generating attractive headlines often learn directly from data, which bases attractiveness on the number of user clicks and views. Although clicks or views do reflect user interest, they can fail to reveal how much interest is raised by the writing style and how much is due to the event or topic itself. Also, such approaches can lead to harmful inventions by over-exaggerating the content, aggravating the spread of false information. In this work, we propose HonestBait, a novel framework for solving these issues from another aspect: generating headlines using forward references (FRs), a writing technique often used for clickbait. A self-verification process is included during training to avoid spurious inventions. We begin with a preliminary user study to understand how FRs affect user interest, after which we present PANCO, an innovative dataset containing pairs of fake news with verified news for attractive but faithful news headline generation. Auto matic metrics and human evaluations show that our framework yields more attractive results (+11.25% compared to human-written verified news headlines) while maintaining high veracity, which helps promote real information to fight against fake news.
Anthology ID:
2023.findings-acl.296
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4810–4824
Language:
URL:
https://aclanthology.org/2023.findings-acl.296
DOI:
10.18653/v1/2023.findings-acl.296
Bibkey:
Cite (ACL):
Chih Yao Chen, Dennis Wu, and Lun-Wei Ku. 2023. HonestBait: Forward References for Attractive but Faithful Headline Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4810–4824, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
HonestBait: Forward References for Attractive but Faithful Headline Generation (Chen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.296.pdf