{"slug": "autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation", "title": "AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism", "summary": "Researchers present AutoJourn, a system for multi-perspective news generation and bias-aware evaluation using large language models, that extracts diverse perspectives from social media, generates balanced summaries, and detects or mitigates bias in AI-generated news. The pipeline shows improvements over baselines in semantic diversity, summary quality, and bias reduction while maintaining content fidelity, with a live demo available.", "body_md": "arXiv:2607.18983v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation", "canonical_source": "https://www.machinebrief.com/news/autojourn-multi-perspective-summarisation-bias-detection-and-2tur", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 04:09:49.278923+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-ethics", "ai-tools", "generative-ai"], "entities": ["AutoJourn"], "alternates": {"html": "https://wpnews.pro/news/autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation", "markdown": "https://wpnews.pro/news/autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation.md", "text": "https://wpnews.pro/news/autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation.txt", "jsonld": "https://wpnews.pro/news/autojourn-multi-perspective-summarisation-bias-detection-and-bias-neutralisation.jsonld"}}