用微调语言模型提升新闻隐含叙事识别与解释准确性
Improving Narrative Classification and Explanation via Fine Tuned Language Models
- 用召回优化的BERT模型检测新闻中的多标签叙事
- 结合GPT-4o与结构化知识表，提升解释的准确性和一致性
- 适合媒体分析、教育和情报领域使用
理解隐性叙事和潜在信息对分析偏见与情绪至关重要。传统NLP方法难以捕捉细微措辞和隐藏意图。本研究解决两大挑战：(1) 新闻文章中叙事与子叙事的多标签分类；(2) 生成简洁、基于证据的主导叙事解释。我们采用召回导向的微调策略优化BERT模型以实现全面叙事检测，并通过GPT-4o流水线修正预测结果以保证一致性。在解释生成方面，提出基于语义检索的Few-shot提示的ReACT框架，确保解释有据可依。为提升事实准确率并减少幻觉，引入结构化分类表作为辅助知识库。实验表明，在提示中整合辅助知识可显著提升分类准确率与解释可靠性，适用于媒体分析、教育及情报收集。
原文摘要 · Abstract (English)
Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predictions using a GPT-4o pipeline for consistency. For narrative explanation, we propose a ReACT (Reasoning + Acting) framework with semantic retrieval-based few-shot prompting, ensuring grounded and relevant justifications. To enhance factual accuracy and reduce hallucinations, we incorporate a structured taxonomy table as an auxiliary knowledge base. Our results show that integrating auxiliary knowledge in prompts improves classification accuracy and justification reliability, with applications in media analysis, education, and intelligence gathering.
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。