两篇新研究论文探讨了大型语言模型（LLM）在检测具有文化特异性的健康虚假信息方面的局限性，特别关注在YouTube上推广牛尿作为印度的一种疗法。研究强调，通常在西方数据上训练的LLM难以分析融合了传统语言和伪科学声明的内容。研究人员发现，仅靠提示工程不足以克服这种文化偏见，表明需要更具文化敏感性的AI分析工具。 AI
影响 强调了开发和评估具有文化意识的LLM以有效打击全球虚假信息的需求。
排序理由 该集群包含两篇arXiv论文，详细介绍了对LLM分析具有文化特异性虚假信息局限性的研究。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2604.22002v1 Announce Type: new Abstract: Social media platforms have become primary channels for health information in the Global South. Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model (LLM)-assisted dis…
arXiv:2604.22606v1 Announce Type: new Abstract: Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sounding claims. These dynamics are not only global but also deeply local, manifestin…
Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sounding claims. These dynamics are not only global but also deeply local, manifesting in culturally specific controversies that requ…
Social media platforms have become primary channels for health information in the Global South. Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model (LLM)-assisted discourse analysis of 30 multilingual transcripts s…