HonestBait: Forward References for Attractive but Faithful Headline Generation

TL;DR

HonestBait introduces a novel headline generation framework using forward references and self-verification, producing more attractive yet faithful headlines to combat fake news.

Contribution

The paper proposes a new framework for headline generation that leverages forward references and self-verification to improve attractiveness and veracity.

Findings

Generated headlines are 11.25% more attractive than verified news headlines.

The framework maintains high veracity while enhancing attractiveness.

The PANCO1 dataset provides pairs of fake and verified news for training and evaluation.

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 PANCO1, an innovative dataset containing pairs of fake news with verified news for attractive but faithful news headline generation. Automatic 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.