# Explaining News Bias Detection: A Comparative SHAP Analysis of Transformer Model Decision Mechanisms

arXiv: https://arxiv.org/abs/2512.23835 · HTML: https://mlsanity.com/paper/2512.23835/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Explainable AI for Trees: From Local Explanations to Global Understanding](https://mlsanity.com/paper/1905.04610/) (2019)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [A Domain-adaptive Pre-training Approach for Language Bias Detection in News](https://mlsanity.com/paper/2205.10773/) (2022)
- [To Bias or Not to Bias: Detecting bias in News with bias-detector](https://mlsanity.com/paper/2505.13010/) (2025)

## Abstract (arXiv)

Automated bias detection in news text is heavily used to support journalistic analysis and media accountability, yet little is known about how bias detection models arrive at their decisions or why they fail. In this work, we present a comparative interpretability study of two transformer-based bias detection models: a bias detector fine-tuned on the BABE dataset and a domain-adapted pre-trained RoBERTa model fine-tuned on the BABE dataset, using SHAP-based explanations. We analyze word-level attributions across correct and incorrect predictions to characterize how different model architectures operationalize linguistic bias. Our results show that although both models attend to similar categories of evaluative language, they differ substantially in how these signals are integrated into predictions. The bias detector model assigns stronger internal evidence to false positives than to true positives, indicating a misalignment between attribution strength and prediction correctness and contributing to systematic over-flagging of neutral journalistic content. In contrast, the domain-adaptive model exhibits attribution patterns that better align with prediction outcomes and produces 63% fewer false positives. We further demonstrate that model errors arise from distinct linguistic mechanisms, with false positives driven by discourse-level ambiguity rather than explicit bias cues. These findings highlight the importance of interpretability-aware evaluation for bias detection systems and suggest that architectural and training choices critically affect both model reliability and deployment suitability in journalistic contexts.