AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism

2026-07-21

AI Summary

This work addresses the limitations of automated journalism—namely, single-perspective reporting, concealed biases, and content imbalance—by proposing a responsible AI-driven news generation system. The system aggregates diverse viewpoints from social media and employs a multi-perspective fusion summarization module to produce news articles that preserve stance diversity. It further integrates fine-grained bias classification with an automatic neutralization mechanism. Innovatively combining advanced prompt engineering, optional retrieval augmentation, and sentence-level bias analysis, the framework enables users to interactively inspect and rewrite outputs. Experimental results demonstrate that the proposed approach significantly outperforms strong baselines in semantic diversity, summary quality, and bias mitigation, while maintaining high content fidelity. An open-access online demo is provided to showcase the system’s capabilities.

Abstract

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.

Problem

• automated journalism
• bias detection
• multi-perspective summarisation
• LLM-generated news
• bias neutralisation

Innovation

• multi-perspective summarisation
• bias detection
• bias neutralisation
• automated journalism
• large language models