EMNLP Findings2023
Mitigating Framing Bias with Polarity Minimization Loss
Yejin Bang, Nayeon Lee, Pascale Fung
Abstract
Framing bias plays a significant role in exacerbating political polarization by distorting the perception of actual events. Media outlets with divergent political stances often use polarized language in their reporting of the same event.
We propose a new loss function that encourages the model to minimize the polarity difference between the polarized input articles to reduce framing bias. Specifically, our loss is designed to jointly optimize the model to map polarity ends bidirectionally. Our experimental results demonstrate that incorporating the proposed polarity minimization loss leads to a substantial reduction in framing bias when compared to a BART-based multi-document summarization model. Notably, we find that the effectiveness of this approach is most pronounced when the model is trained to minimize the polarity loss associated with informational framing bias (i.e., skewed selection of information to report).
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Measuring Political Bias in Large Language Models: What Is Said and How It Is Said cites We Can Detect Your Bias: Predicting the Political Ideology of News Articles
- Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation cites We Can Detect Your Bias: Predicting the Political Ideology of News Articles
Cited by top-tier papers2
- Measuring Political Bias in Large Language Models: What Is Said and How It Is SaidYejin Bang, Delong Chen, Nayeon Lee, Pascale FungACL 2024 · 21 citations
- Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias MitigationYuanyuan Lei, Ruihong HuangACL 2025
Builds on3
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- We Can Detect Your Bias: Predicting the Political Ideology of News ArticlesRamy Baly, Giovanni Da San Martino, James R. Glass, Preslav NakovEMNLP 2020 · 6 citations
Related papers
- Measuring and Mitigating Media Outlet Name Bias in Large Language ModelsSeong-Jin Park, Kang-Min KimEMNLP 2025
- All Things Considered: Detecting Partisan Events from News Media with Cross-Article ComparisonYujian Liu, Xinliang Frederick Zhang, Kaijian Zou, Ruihong Huang et al.EMNLP 2023 · 1 citation
- Disentangling Structure and Style: Political Bias Detection in News by Inducing Document HierarchyJiwoo Hong, Yejin Cho, Jiyoung Han, Jaemin Jung et al.EMNLP Findings 2023 · 4 citations
- Leveraging Lead Bias for Zero-shot Abstractive News SummarizationChenguang Zhu, Ziyi Yang, Robert Gmyr, Michael Zeng et al.SIGIR 2021 · 23 citations
- SumREN: Summarizing Reported Speech about Events in NewsRevanth Gangi Reddy, Heba Elfardy, Hou Pong Chan, Kevin Small et al.AAAI 2023 · 7 citations
