HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification

• URL: http://arxiv.org/abs/2606.26100v1
• Date: Wed, 29 Apr 2026 18:33:42 GMT
• Title: HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification
• Abstract summary: We present textbfHierBias, a hierarchical context-conditioned media bias detector.<n>We introduce the emphcontext-conditioned bias probability and prove theoretically that leveraging document context strictly reduces the Bayes error of sentence-level classification.
• Score: 6.417595716293325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Media bias detection is a critical task for ensuring fair and balanced information dissemination, yet existing sentence-level approaches classify each sentence independently, ignoring inter-sentence contextual signals that human annotators naturally exploit. We present \textbf{HierBias}, a hierarchical context-conditioned media bias detector that formally models document context in bias prediction. We introduce the \emph{context-conditioned bias probability} and prove theoretically that leveraging document context strictly reduces the Bayes error of sentence-level classification when inter-sentence mutual information is non-zero. A multi-task generalization bound further establishes that jointly training binary bias detection and fine-grained bias type classification improves sample efficiency on small annotated corpora. Architecturally, HierBias pairs a sentence-level RoBERTa encoder with a cross-sentence Transformer aggregator and dual output heads for binary detection and four-class type classification. Evaluated on BABE and BASIL, HierBias achieves 0.853 F1 and 0.723 MCC, surpassing the state-of-the-art bias-detector by $+2.6\%$ F1 and $+4.3\%$ MCC (McNemar's test, $p < 0.05$). Ablation experiments confirm that each theoretical component contributes independently and consistently.

Related papers

• Simplex Relaxation for Discrete Diffusion [58.33696160279345]
  We introduce Simplax, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable.<n>Simplax improves the generative perplexity--entropy tradeoff on unconditional OpenWebText generation.
  arXiv  Detail & Related papers  (2026-08-11T07:58:17Z)
• Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers [3.5347586732342435]
  We argue that a demographically-conditioned synthetic generator can do both: mitigate bias on the training side and detect bias on the evaluation side.<n>For bias mitigation (training), a demographically-balanced synthetic cohort is most useful as a pretraining prior, not as joint augmentation.<n>The synthetic estimator reproduces the subgroup ranking of a well-powered real oracle.
  arXiv  Detail & Related papers  (2026-07-16T13:36:48Z)
• Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News [1.4465033892011254]
  We present two approaches for classifying sentences from German-language climate news articles as threat-oriented, solution-oriented, both, or neither.<n>The first approach uses few-shot prompting with an open-weights large language model (Llama 4 Maverick), employing chain-of-thought reasoning and structured output with confidence scoring.<n>The second approach fine-tunes a German BERT model (deepset/gbert-large) for sentence-pair classification, where the preceding sentence provides contextual information for the target sentence.
  arXiv  Detail & Related papers  (2026-06-25T00:48:40Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• To Bias or Not to Bias: Detecting bias in News with bias-detector [1.8024397171920885]
  We perform sentence-level bias classification by fine-tuning a RoBERTa-based model on the expert-annotated BABE dataset.<n>We show statistically significant improvements in performance when comparing our model to a domain-adaptively pre-trained DA-RoBERTa baseline.<n>Our findings contribute to building more robust, explainable, and socially responsible NLP systems for media bias detection.
  arXiv  Detail & Related papers  (2025-05-19T11:54:39Z)
• Towards Distribution-Agnostic Generalized Category Discovery [51.52673017664908]
  Data imbalance and open-ended distribution are intrinsic characteristics of the real visual world. We propose a Self-Balanced Co-Advice contrastive framework (BaCon) BaCon consists of a contrastive-learning branch and a pseudo-labeling branch, working collaboratively to provide interactive supervision to resolve the DA-GCD task.
  arXiv  Detail & Related papers  (2023-10-02T17:39:58Z)
• Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection [24.35462897801079]
  We introduce the Media Bias Identification Benchmark (MBIB) to group different types of media bias under a common framework. After reviewing 115 datasets, we select nine tasks and carefully propose 22 associated datasets for evaluating media bias detection techniques. Our results suggest that while hate speech, racial bias, and gender bias are easier to detect, models struggle to handle certain bias types, e.g., cognitive and political bias.
  arXiv  Detail & Related papers  (2023-04-25T20:49:55Z)
• Self-supervised debiasing using low rank regularization [59.84695042540525]
  Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. We propose a self-supervised debiasing framework potentially compatible with unlabeled samples. Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
  arXiv  Detail & Related papers  (2022-10-11T08:26:19Z)
• Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts [24.51774048437496]
  This paper presents BABE, a robust and diverse data set for media bias research. It consists of 3,700 sentences balanced among topics and outlets, containing media bias labels on the word and sentence level. Based on our data, we also introduce a way to detect bias-inducing sentences in news articles automatically.
  arXiv  Detail & Related papers  (2022-09-29T05:32:55Z)
• Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection [81.07346419422605]
  Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. We propose a novel hierarchical semi-supervised contrastive learning framework, for contamination-resistant anomaly detection.
  arXiv  Detail & Related papers  (2022-07-24T18:49:26Z)
• Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition [80.07843757970923]
  We show that existing OOD detection methods suffer from significant performance degradation when the training set is long-tail distributed. We propose Partial and Asymmetric Supervised Contrastive Learning (PASCL), which explicitly encourages the model to distinguish between tail-class in-distribution samples and OOD samples. Our method outperforms previous state-of-the-art method by $1.29%$, $1.45%$, $0.69%$ anomaly detection false positive rate (FPR) and $3.24%$, $4.06%$, $7.89%$ in-distribution
  arXiv  Detail & Related papers  (2022-07-04T01:53:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.