# A Multi-Dimensional Evaluation of Explainability in Media Bias Detection

arXiv: https://arxiv.org/abs/2607.19954 · HTML: https://mlsanity.com/paper/2607.19954/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Self-Attention Attribution: Interpreting Information Interactions Inside Transformer](https://mlsanity.com/paper/2004.11207/) (2020)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [From Understanding to Utilization: A Survey on Explainability for Large Language Models](https://mlsanity.com/paper/2401.12874/) (2024)
- [How Interpretable are Reasoning Explanations from Prompting Large Language Models?](https://mlsanity.com/paper/2402.11863/) (2024)
- [The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias](https://mlsanity.com/paper/2312.16148/) (2023)
- [LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains](https://mlsanity.com/paper/2407.14344/) (2024)
- [Data-Centric Human Preference with Rationales for Direct Preference Alignment](https://mlsanity.com/paper/2407.14477/) (2024)
- [Adaptable and Reliable Text Classification using Large Language Models](https://mlsanity.com/paper/2405.10523/) (2024)
- [On Explaining with Attention Matrices](https://mlsanity.com/paper/2410.18541/) (2024)
- [When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation](https://mlsanity.com/paper/2604.21309/) (2026)

## Abstract (arXiv)

Detecting media bias automatically is difficult because biased framing is often subtle, yet in domains such as news analysis, accurate predictions alone are insufficient without explanations that reflect the model's underlying reasoning. We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias Annotations By Experts (BABE) dataset. Specifically, we study BERT and RoBERTa as classifiers (base and large variants) along three complementary axes: predictive performance, explanation plausibility (token-level alignment with expert rationales), and mechanistic faithfulness (whether compact sets of attention heads recover predictive signal under counterfactual rationale masking). To induce variation in plausibility, we additionally investigate attention-supervised finetuning, which incorporates expert rationale annotations as an auxiliary training signal. Attention supervision serves as an intervention on attribution plausibility, while the effectiveness of attribution methods varies substantially across architectures. Circuit analysis further reveals substantial variation in mechanistic recoverability across architectures, suggesting that model scale alone does not determine circuit compressibility. Taken together, our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior and should be evaluated separately when studying explainability in media bias detection.