发表机构
Technical University of Munich; Sapienza University of Rome（慕尼黑工业大学; 罗马第一大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoJourn系统旨在应对自动新闻中多视角新闻生成及偏差问题，通过整合提示工程与检索增强等，产生多样视角集，经多视角摘要模块和偏差分析套件，实现不同视角提取、平衡摘要生成及偏差检测与中和，评估显示其优于基线且保持内容保真。
AI 中文摘要
我们展示了AutoJourn，一个用于使用大语言模型进行多视角新闻生成和偏差感知评估的演示系统。该系统解决了负责任的自动新闻中的三个核心挑战：从非结构化社交媒体讨论中提取不同视角，生成保留观点多样性的摘要，以及检测或减轻人工智能生成新闻中的偏差。其流程整合了先进的提示工程与可选的检索增强，以产生语义多样的视角集，一个将冲突观点合并为平衡摘要的多视角摘要模块，以及一个支持生成新闻文章中句子级偏差检测、类型分类和自动中和的偏差分析套件。用户可以在界面中检查视角簇、比较特定立场的摘要、生成新闻文章并应用偏差感知重写。我们用内在指标评估每个组件——语义多样性、摘要质量和偏差减少，并在保持内容保真度的同时，显示出优于强大基线的改进。本文还附带了一个可公开访问的实时演示，以促进对社会责任自动新闻的可重复性和进一步研究。
英文摘要
We present AutoJourn, a demonstration system for multi-perspective news generation and bias-aware evaluation using large language models (LLMs). The system tackles three core challenges in responsible automated journalism: extracting diverse perspectives from unstructured social media discussions, generating summaries that preserve viewpoint diversity, and detecting or mitigating bias in AI-generated news. The pipeline integrates advanced prompt engineering with optional retrieval augmentation to produce semantically diverse perspective sets, a multi-perspective summarisation module that merges conflicting viewpoints into balanced summaries, and a bias analysis suite supporting sentence-level bias detection and type classification in the generated news article, and automatic neutralisation. Users can inspect perspective clusters, compare stance-specific summaries, generate news articles, and apply bias-aware rewrites directly in the interface. We evaluate each component with intrinsic metrics -- semantic diversity, summary quality, and bias reduction and show improvements over strong baselines while maintaining content fidelity. A live, publicly accessible demo accompanies the paper to facilitate reproducibility and further research on socially responsible automated journalism.
