识别并非逆转：事实保持新闻框架的受控反转测试

中文摘要 AI 辅助

大型语言模型（LLMs）越来越多地被用于分析和改写新闻，然而当前的框架研究主要评估生成、检测或改写后的文本是否显得更中立。这些研究并未直接证明模型能否在保持事实不变的情况下撤销已知的框架转换。我们针对框架的三种既定文本实现形式——评价性词汇、施事性实现和信息显著性——引入了一项受控反转测试。在60篇新闻文章和三种干预强度下，这产生了540对保留原子事实并记录编辑的配对变体。在Qwen、DeepSeek和Kimi上，事实保持率接近0.84，而干预反转率为0.044至0.068。即使框架类型和方向都被正确识别，汇总反转率也仅为0.071。这些结果揭示了事实保真度、框架识别和框架反转之间的明显分离：识别一篇文章的框架方式并不意味着该框架可以被撤销。

英文摘要

Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing studies mainly evaluate generation, detection, or whether rewritten text appears more neutral. They do not directly show whether a model can undo a known framing transformation while keeping the facts fixed. We introduce a controlled inversion test over three established textual realizations of framing: evaluative lexis, agency realization, and information salience. Across 60 news articles and three intervention strengths, this yields 540 paired variants with preserved atomic facts and recorded edits. Across Qwen, DeepSeek, and Kimi, factual preservation remains near 0.84, whereas intervention reversal is 0.044--0.068. Even when both framing type and direction are recognized correctly, pooled reversal reaches 0.071. These results reveal a clear separation between factual fidelity, framing recognition, and framing inversion: recognizing how an article is framed does not imply that the framing can be undone.

发表机构

• University of Science and Technology of China（中国科学技术大学）

机构由 AI 辅助整理，请以论文原文为准。