NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias
This work addresses the issue of political polarization and bias in news consumption for the general public and media analysts, though it is incremental as it builds on existing summarization techniques with a specific focus on neutrality.
The authors tackled the problem of media framing bias by proposing a new task of generating neutral summaries from multiple news articles with varying political leanings, and introduced a dataset, metric, and model (NeuS-TITLE) that achieved effective mitigation by leveraging title signals for hierarchical neutralization.
Media news framing bias can increase political polarization and undermine civil society. The need for automatic mitigation methods is therefore growing. We propose a new task, a neutral summary generation from multiple news articles of the varying political leanings to facilitate balanced and unbiased news reading. In this paper, we first collect a new dataset, illustrate insights about framing bias through a case study, and propose a new effective metric and model (NeuS-TITLE) for the task. Based on our discovery that title provides a good signal for framing bias, we present NeuS-TITLE that learns to neutralize news content in hierarchical order from title to article. Our hierarchical multi-task learning is achieved by formatting our hierarchical data pair (title, article) sequentially with identifier-tokens ("TITLE=>", "ARTICLE=>") and fine-tuning the auto-regressive decoder with the standard negative log-likelihood objective. We then analyze and point out the remaining challenges and future directions. One of the most interesting observations is that neural NLG models can hallucinate not only factually inaccurate or unverifiable content but also politically biased content.