探索LLM在处理政治争议文档时，不同提示语言如何引发意识形态分歧，揭示语言偏见对模型立场的微妙影响。
arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingu…
揭露AI生成语言暗中强化标准语言意识形态，关乎语言多样性与公平性
arXiv:2406.08726v3 Announce Type: replace Abstract: Large language models (LLMs) generate text that reinforces standard language ideology: a bias towa…
开源大模型面对俄语虚假信息时，语言切换竟会引发意识形态“站队”，这篇研究揭示了AI安全新维度。
arXiv:2606.08512v1 Announce Type: cross Abstract: As Russia's war against Ukraine extends into generative AI, large language models (LLMs) adapted for…
探讨新闻话题情感是否影响人们对政治立场的感知，并对比人与LLM的标注差异，揭示大模型在意识形态推断上的潜力与局限。
arXiv:2606.06715v1 Announce Type: cross Abstract: We ask whether topic sentiment has a causal effect on perceived political ideology, and whether the …
探讨Wikipedia和HN等平台如何避免意识形态渗透，并揭示其对LLM训练数据偏见的影响。
Someone submitted a link [1] to an article on Wikipedia's whitewashing of Mao titled Wikipedia Whitewashes Mao – The Anatomy of Ideological Capture [2…
从历史与意识形态角度剖析美国共和党税收极端主义的根源，挑战“政府是外人”的流行叙事。
Andrew Winston writing for Ev’s blog : ...consider the way so many Americans talk about government, like it’s some external group. It’s bizarre. We ar…