标签
本文提出一个二维框架用于分析新闻标题,区分显著性框架和选择框架,并将其应用于对French新闻标题的大规模审计,采用基于LLM的标注方法,揭示了媒体框架中的差异。
This paper empirically evaluates how well LLMs align with human emotional perception of news framing, using a YouGov survey of 3,011 UK adults and seven LLMs assessing sympathy in headlines. It finds that alignment varies across models and demographic subgroups, highlighting the importance of differential alignment for AI development.
实验研究显示,在标题中插入第一/第二人称代词对人类记忆度影响不一,且大语言模型常生成不准确或不自然的改写。