Large Language Models (LLMs) are increasingly integrated into critical decision-making processes, such as loan approvals and visa applications, where inherent biases can lead to discriminatory outcomes. In this paper, we examine the nuanced relationship between demographic attributes and socioeconomic biases in LLMs, a crucial yet understudied area of fairness in LLMs. We introduce a novel dataset of one million English sentences to systematically quantify socioeconomic biases across various demographic groups. Our findings reveal pervasive socioeconomic biases in both established models such as GPT-2 and state-of-the-art models like Llama 2 and Falcon. We demonstrate that these biases are significantly amplified when considering intersectionality, with LLMs exhibiting a remarkable capacity to extract multiple demographic attributes from names and then correlate them with specific socioeconomic biases. This research highlights the urgent necessity for proactive and robust bias mitigation techniques to safeguard against discriminatory outcomes when deploying these powerful models in critical real-world applications.

翻译：大型语言模型正日益融入贷款审批和签证申请等关键决策流程，其内在偏见可能导致歧视性结果。本文研究了大型语言模型中人口属性与社会经济偏见之间微妙的关系，这是LLM公平性研究中至关重要却尚未得到充分探索的领域。我们引入了一个包含一百万句英语文本的新型数据集，用于系统量化不同人口群体的社会经济偏见。研究结果表明，无论是GPT-2等经典模型还是Llama 2、Falcon等前沿模型，均普遍存在社会经济偏见。我们证明，当考虑交叉性时，这些偏见会被显著放大——LLMs展现出从姓名中提取多重人口属性并将其与特定社会经济偏见相关联的显著能力。本研究强调，在关键现实场景中部署这些强大模型时，迫切需要采取主动且稳健的偏见缓解技术，以防止产生歧视性后果。