arXiv cs.CL· Mo Zhou, Yiwei Zhang·· 10 小时前AI 评分45
大语言模型的框架诱导脆弱性：来自中文新闻标题的证据
Framing-Induced Vulnerability in Large Language Models: Evidence from Chinese News Headlines
AI 导读
对 63,926 条中文新闻标题的生态审计与受控实验显示，仅改变标题框架即可同时改变大语言模型判断的误导性与事件严重度，且 DeepSeek、MiMo、Dots、LongCat 四个中文模型的偏移方向与排序一致。
正文 · 原文
Abstract:Large language models increasingly evaluate, route, and moderate news, so a model's judgment of a headline has become a gatekeeping decision. We ask whether that judgment follows the fact being reported or the way the fact is framed. We combine an ecological audit of 63,926 Chinese news headlines with a controlled experiment. The experiment covers 30 real events, 30 synthetic events, and 29 natural headline pairs, tested on four Chinese models. Changing only the headline frame shifted both perceived misleadingness and event severity, and the direction and ordering of the shifts were the same for DeepSeek, MiMo, Dots, and LongCat. Emotionally intensified headlines raised severity ratings by 0.65 to 0.88 points, whereas positively reframed headlines lowered them by 0.34 to 0.52 points. Supplying the article body reduced this severity bias by 54 to 80 percent, and all four reductions were significant at p < .01. A small human reference study showed the same direction of effect. Headline-only LLM evaluation therefore carries a measurable robustness gap, and framing sensitivity belongs among the reliability properties that deployment and governance check.
| Comments: | 7 pages, 5 figures |
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7; J.4 |
| Cite as: | arXiv:2611.13531 [cs.CL] |
| (or arXiv:2611.13531v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13531 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mo Zhou [view email]
[v1]
Tue, 10 Nov 2026 03:54:03 UTC (65 KB)
来源：arXiv cs.CL · arxiv.org