印度金融自动建议偏差(IFAAB)数据集:审计印度大语言模型生成金融建议中的社会经济与人口统计学差异
The Indian Financial Automated Advice Bias (IFAAB) Dataset : Auditing Socioeconomic and Demographic Disparities in LLM-Generated Financial Advice in India
AI总结:
该研究推出IFAAB基准数据集,发现GPT-4o生成的印度金融建议存在性别、种姓等差异,加入地区信息可缩小性别差距,为评估LLM金融建议的公平性提供了基准。
摘要:
大型语言模型正越来越多地被用于金融指导,但在全球南方语境中,其建议是否会因社会身份不同而发生变化,目前人们知之甚少。我们推出了印度金融自动建议偏差(IFAAB)基准,这是一个包含31734条GPT-4o生成的金融建议回复的反事实审计数据集,针对的是具有不同性别、种姓、教育程度、就业状况、居住地、年龄和地区的合成印度人物。在保持基础请求不变的情况下,我们评估了大语言模型隐含的财富、收入、储蓄、预期收益、文本相似度、建议主题以及定性偏差判断方面的差异。在仅针对性别的审计中,带有男性标签的人物获得的初始总资源比具有可比性的带有女性标签的人物高60.1%,建议后的总资源则高46.8%;在加入种姓信息的审计中,建议后的总资源差距仍为49.4%。加入地区信息后,总体建议后的总资源性别差距缩小至7.9%,这表明存在强烈的地理条件影响。单独的种姓比较也显示出系统性分层:相对于普通类别的人物,其他落后阶层(OBC)、表列种姓(SC)和表列部落(ST)的人物获得的建议后总资源显著更低。文本审计显示,成对的性别相关回复之间的语义相似度较低,平均TF-IDF余弦相似度得分为0.44。定性分析表明,女性更常被引导采取谨慎储蓄、寻求社区支持和学习基础金融知识的方向,而男性则获得更多涉及投资、创业和资产积累的增长导向型建议。IFAAB为评估大语言模型介导的金融建议中的公平性、适用性和消费者保护风险提供了可重复使用的基准,并强调在高风险经济领域需要对人工智能系统进行基于本地的交叉评估。
英文摘要:
Large language models are increasingly used for financial guidance, yet little is known about whether their advice changes across social identities in Global South contexts. We introduce the Indian Financial Automated Advice Bias (IFAAB) benchmark, a counterfactual audit dataset of 31,734 GPT-4o-generated financial-advice responses for synthetic Indian personas varying by gender, caste, education, employment, residence, age, and district. Holding the underlying request fixed, we evaluate disparities in LLM-implied wealth, income, savings, projected gains, textual similarity, advice topics, and qualitative bias judgments. In the gender-only audit, male-labelled profiles receive 60.1\% higher initial total resources and 46.8\% higher post-advice total resources than comparable female-labelled profiles; in the caste-augmented audit, the post-advice total-resource gap remains 49.4\%. Adding district information reduces the aggregate post-advice total-resource gender gap to 7.9\%, revealing strong geographic conditioning. Standalone caste comparisons also show systematic stratification: relative to General-category profiles, OBC, SC, and ST profiles receive significantly lower post-advice total resources, respectively. Textual audits show low semantic similarity between paired gendered responses, with an average TF--IDF cosine similarity score of 0.44. Qualitative analysis shows that women are more often steered toward cautious saving, community support, and basic financial literacy, while men receive more growth-oriented advice involving investment, entrepreneurship, and asset accumulation. IFAAB provides a reusable benchmark for evaluating fairness, suitability, and consumer-protection risks in LLM-mediated financial advice, and highlights the need for locally grounded, intersectional evaluation of AI systems in high-stakes economic domains.
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。