大型语言模型中偏见的系统分析
A Multifaceted Analysis of Social Biases in Large Language Models
AI总结：
本文系统分析了四种广泛使用的大型语言模型在政治、意识形态、联盟、语言和性别等维度上的偏见，通过多项实验揭示了模型在中立性、意识形态倾向、地缘政治倾向、多语言故事完成中的偏见以及性别倾向。
摘要：
大型语言模型（LLMs）已迅速成为获取信息和支持人类决策不可或缺的工具。然而，确保这些模型在各种情境下保持公平性对于其安全和负责任的部署至关重要。在本研究中，我们对四种广泛采用的LLMs进行了全面分析，探讨了它们在政治、意识形态、联盟、语言和性别等维度上的潜在偏见和倾向。通过一系列精心设计的实验，我们利用新闻摘要来检验其政治中立性，通过新闻立场分类来研究意识形态偏见，通过联合国投票模式来探讨对特定地缘政治联盟的倾向，通过多语言故事完成来检验语言偏见，并通过世界价值观调查中的响应来揭示性别相关倾向。结果表明，尽管这些模型被设计为中立和公正，但它们仍然表现出不同类型的偏见和倾向。
英文摘要：
Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and responsible deployment. In this study, we undertake a comprehensive examination of four widely adopted LLMs, probing their underlying biases and inclinations across the dimensions of politics, ideology, alliance, language, and gender. Through a series of carefully designed experiments, we investigate their political neutrality using news summarization, ideological biases through news stance classification, tendencies toward specific geopolitical alliances via United Nations voting patterns, language bias in the context of multilingual story completion, and gender-related affinities as revealed by responses to the World Values Survey. Results indicate that while the LLMs are aligned to be neutral and impartial, they still show biases and affinities of different types.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
