cd /news/natural-language-processing/hierbias-context-conditioned-hierarc… · home topics natural-language-processing article
[ARTICLE · art-40231] src=arxiv.org ↗ pub= topic=natural-language-processing verified=true sentiment=↑ positive

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

Researchers introduced HierBias, a hierarchical context-conditioned media bias detector that models document context to improve sentence-level bias classification. The system achieved 0.853 F1 and 0.723 MCC on BABE and BASIL benchmarks, surpassing the state-of-the-art by 2.6% F1 and 4.3% MCC. The approach includes a multi-task framework for binary detection and fine-grained bias type classification, with theoretical guarantees on error reduction.

read1 min views1 publishedJun 26, 2026

arXiv:2606.26100v1 Announce Type: new 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.

── more in #natural-language-processing 4 stories · sorted by recency
── more on @hierbias 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/hierbias-context-con…] indexed:0 read:1min 2026-06-26 ·