English(EN) Framing-Induced Vulnerability in Large Language Models: Evidence from Chinese News Headlines

研究揭示大型语言模型易受新闻标题框架影响

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

一项新近发表在arXiv上的研究调查了大型语言模型（LLMs）如何受到新闻标题框架的影响。研究人员发现，仅改变标题的措辞，而不改变事实本身，就会显著影响模型对事件严重性和误导性的感知。这种框架效应在中国测试的四种大型语言模型（包括DeepSeek和LongCat）中均表现一致。研究表明，大型语言模型在仅基于标题的评估中表现出可衡量的鲁棒性差距，凸显了对框架敏感性进行治理检查的必要性。 AI

影响强调了大型语言模型新闻评估中的一个关键漏洞，暗示了潜在的操纵可能性以及在已部署系统中加强鲁棒性检查的必要性。

排序理由学术论文，详细介绍了关于大型语言模型行为的研究结果。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 36 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了关于大型语言模型行为的研究结果。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Mo Zhou, Yiwei Zhang · 2026-11-11 05:00

大型语言模型中的框架诱导漏洞：来自中国新闻标题的证据

arXiv:2611.13531v1 Announce Type: new 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…

本文如何被排名

报道来源 [1]

大型语言模型中的框架诱导漏洞：来自中国新闻标题的证据

相关实体

相关话题