English(EN) Political Ideology Shifts in Large Language Models

研究：LLM的意识形态表达随角色设定而转变

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

一项发表在arXiv上的新研究探讨了合成角色设定如何影响大型语言模型的意识形态表达。研究人员使用政治罗盘测试（Political Compass Test）对七个经过指令微调的模型进行了探测，发现与较小的模型（70-80亿参数）相比，较大的模型（700亿+参数）表现出更广泛的隐性意识形态覆盖范围。明确的意识形态引导显著改变了模型的响应，其中右翼威权主义提示被证明特别有效。研究还指出，角色描述中与主题相关的内容会系统性地改变意识形态输出，凸显了LLM在政治敏感环境中的可塑性。 AI

影响揭示了LLM响应如何被角色设定所操纵，从而影响其在敏感应用中被感知的公正性和安全性。

排序理由关于LLM行为的学术论文。[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: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM行为的学术论文。[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) · Pietro Bernardelle, Stefano Civelli, Leon Fr\"ohling, Riccardo Lunardi, Kevin Roitero, Gianluca Demartini · 2026-09-01 04:00

大型语言模型中的政治意识形态转变

arXiv:2508.16013v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological biases. In this work, we examine how synthetic persona conditioning shapes ideo…

本文如何被排名

报道来源 [1]

大型语言模型中的政治意识形态转变

相关实体

相关话题