NewsLens: A Multi-Agent Framework for Adversarial News Bias Navigation

2026-05-17

AI Summary

This study addresses the limitations of existing media bias detection approaches, which are largely confined to political label classification and fail to pinpoint the location, form, or structural information gaps underlying bias. To overcome this, the work proposes the first multi-agent adversarial pipeline for news bias analysis, integrating five collaborative agents—Fact Verifier, a dual-perspective framework analyzer, Propaganda Detector, and Neutral Summarizer—built upon open-source large language models such as Qwen2.5-3B-Instruct (4-bit) and Mistral 7B. This system enables fine-grained deconstruction and visualization of ideological omissions, rhetorical manipulation, and reporting boundaries. Experiments across four geopolitical event datasets reveal that centrist outlets exhibit the greatest perspective divergence, while conservative outlets show the highest manipulation scores. Ablation studies further demonstrate that removing the Propaganda Detector substantially reduces the informational completeness of neutral summaries, confirming the framework’s effectiveness and high reproducibility.

Abstract

Media bias detection has predominantly been framed as a classification task: assign a political label to an article or outlet. We argue this framing is too shallow: it identifies that bias exists but not where, how, or crucially, what is structurally omitted. We present NewsLens, a five-agent adversarial pipeline for structured news bias navigation. A Fact Verifier, Progressive Framing Analyst, Conservative Framing Analyst, Propaganda Detector, and Neutral Summarizer collaborate to deconstruct articles into interpretable framing maps, exposing ideological omissions, rhetorical manipulation, and framing boundaries. The system is evaluated on 15 articles across four geopolitical event clusters (India-Pakistan Kashmir, Gaza, Climate Policy, Ukraine) using Qwen2.5-3B-Instruct (4-bit quantised, Google Colab T4), with cross-model validation using Mistral 7B on the Kashmir cluster. Center outlets show the highest mean Perspective Divergence Score (PDS: Qwen 0.907, Mistral 0.729 on Kashmir subset); conservative-framing outlets show the highest mean Manipulation Index (MI: 0.600 across both models). Cross-model comparison shows high consistency for high-propaganda content (Republic World delta-PDS=0.125, MI=0.8 both models) and greater variance for nuanced reporting. Mann-Whitney U tests find no statistically significant between-group differences at n=15, reported honestly as a sample-size limitation confirmed by post-hoc power analysis. A partial ablation removing the Propaganda Detector shows degraded omission precision in the Neutral Summarizer output. The architecture extends prior lexical-geometric bias work to agentic LLM reasoning, and is fully reproducible using open-weight models without API keys.

Problem

• news bias
• media bias detection
• structural omission
• framing analysis
• adversarial navigation

Innovation

• multi-agent framework
• adversarial news bias analysis
• structured framing maps
• LLM-based bias detection
• propaganda and omission identification