用五个智能体协作分析新闻偏见，揭示被隐藏的立场与信息缺失。
NewsLens: A Multi-Agent Framework for Adversarial News Bias Navigation
- 构建五智能体系统，从事实验证到中立摘要全程拆解新闻框架。
- 保守派媒体操纵指数达0.600，主流媒体视角分歧分值高达0.907。
- 适合关注媒体偏见、内容安全与可解释性研究者使用。
媒体偏见检测长期被视为分类任务：给文章或媒体打政治标签。我们认为这种框架过于浅显：仅识别偏见存在，却无法定位其位置、方式，更忽视结构性遗漏。本文提出NewsLens，一个由五个智能体组成的对抗式新闻偏见导航框架——事实验证者、渐进式框架分析者、保守框架分析者、宣传检测器与中立摘要生成器协同工作，将新闻拆解为可解释的框架地图，揭示意识形态遗漏、修辞操控与框架边界。在四个地缘政治事件集群（印巴克什米尔、加沙、气候政策、乌克兰）共15篇文章上评估，使用Qwen2.5-3B-Instruct（4-bit量化，Google Colab T4），并以Mistral 7B在克什米尔子集进行跨模型验证。主流媒体平均视角分歧分值（PDS）达0.907（Qwen）、0.729（Mistral）；保守派媒体操纵指数（MI）均值为0.600。跨模型比较显示高宣传内容一致性高（共和世界delta-PDS=0.125，MI=0.8），而微妙报道差异较大。曼-惠特尼U检验未发现组间显著差异（n=15），报告样本量限制，并经事后功效分析确认。移除宣传检测器的局部消融实验显示中立摘要生成精度下降。该架构将先前的词法-几何偏见方法拓展至基于代理的LLM推理，且完全可复现，仅需开源权重模型，无需API密钥。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。