Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current research findings and discusses the implications of biases in real-world applications. Additionally, we critically assess existing bias mitigation techniques and propose future research directions to enhance fairness and equity in LLMs. This survey serves as a foundational resource for researchers, practitioners, and policymakers concerned with addressing and understanding biases in LLMs.

翻译：大型语言模型（LLMs）通过提供前所未有的文本生成、翻译和理解能力，彻底改变了自然语言处理（NLP）领域的各种应用。然而，其广泛部署也引发了人们对这些模型中嵌入的显著偏见问题的深切关注。本文对LLMs中的偏见进行了全面综述，旨在系统梳理与这些偏见相关的类型、来源、影响及缓解策略。我们将偏见系统地划分为多个维度进行探讨。本综述综合了当前的研究成果，并讨论了偏见在现实世界应用中的潜在影响。此外，我们批判性地评估了现有的偏见缓解技术，并提出了未来研究方向，以提升LLMs的公平性与公正性。本综述为关注LLMs偏见问题及其应对的研究人员、从业者和政策制定者提供了基础性参考资源。