Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training. This research delves into the inherent biases present in masked language models (MLMs), with a specific focus on gender biases. This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT-multilingual, XLM-RoBERTa, and DistilBERT-multilingual. The methodology employed a novel dataset, bifurcated into two subsets: one containing prompts that encouraged models to generate subject pronouns in English, and the other requiring models to return the probabilities of verbs, adverbs, and adjectives linked to the prompts' gender pronouns. The analysis reveals stereotypical gender alignment of all models, with multilingual variants showing comparatively reduced biases.

翻译：语言模型（LMs）已成为技术进步领域的核心力量。尽管其能力广泛且具有变革性，但这些模型往往嵌入了用于训练的人类生成数据集中所蕴含的社会偏见。本研究深入探究了掩码语言模型（MLMs）中存在的固有偏见，特别聚焦于性别偏见。研究评估了六个主要模型：BERT、RoBERTa、DistilBERT、BERT-multilingual、XLM-RoBERTa和DistilBERT-multilingual。研究方法采用了一个新颖的数据集，该数据集被划分为两个子集：一个包含鼓励模型生成英语主语代词的提示，另一个要求模型返回与提示代词相关的动词、副词和形容词的概率。分析揭示了所有模型均存在刻板的性别对齐现象，而多语言变体模型的偏见相对较少。