NeutraSum: A Language Model can help a Balanced Media Diet by Neutralizing News Summaries
Abstract
Media bias in news articles arises from the political polarisation of media outlets, which can reinforce societal stereotypes and beliefs. Reporting on the same event often varies significantly between outlets, reflecting their political leanings through polarised language and focus. Although previous studies have attempted to generate bias-free summaries from multiperspective news articles, they have not effectively addressed the challenge of mitigating inherent media bias. To address this gap, we propose \textbf{NeutraSum}, a novel framework that integrates two neutrality losses to adjust the semantic space of generated summaries, thus minimising media bias. These losses, designed to balance the semantic distances across polarised inputs and ensure alignment with expert-written summaries, guide the generation of neutral and factually rich summaries. To evaluate media bias, we employ the political compass test, which maps political leanings based on economic and social dimensions. Experimental results on the Allsides dataset demonstrate that NeutraSum not only improves summarisation performance but also achieves significant reductions in media bias, offering a promising approach for neutral news summarisation.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2025
- DOI:
- arXiv:
- arXiv:2501.01284
- Bibcode:
- 2025arXiv250101284L
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Artificial Intelligence