This paper presents a comprehensive survey of work on sociodemographic bias in language models (LMs). Sociodemographic biases embedded within language models can have harmful effects when deployed in real-world settings. We systematically organize the existing literature into three main areas: types of bias, quantifying bias, and debiasing techniques. We also track the evolution of investigations of LM bias over the past decade. We identify current trends, limitations, and potential future directions in bias research. To guide future research towards more effective and reliable solutions, we present a checklist of open questions. We also recommend using interdisciplinary approaches to combine works on LM bias with an understanding of the potential harms.

翻译：本文对语言模型中社会人口统计偏见的相关研究进行了全面综述。嵌入在语言模型中的社会人口统计偏见在现实世界部署中可能产生有害影响。我们系统地将现有文献组织为三个主要领域：偏见类型、偏见量化以及去偏技术。同时，我们追踪了过去十年语言模型偏见研究的演变过程，识别了当前趋势、局限性以及潜在的未来研究方向。为引导未来研究走向更有效、更可靠的解决方案，我们提出了一份开放性问题清单，并建议采用跨学科方法，将语言模型偏见研究与对潜在危害的理解相结合。