To address this issue, we formulate translated non-English, geographic, and socioeconomic integrated prompts and evaluate their impact on VL model performance for data from different countries and income groups. Our findings show that geographic and socioeconomic integrated prompts improve VL performance on lower-income data and favor the retrieval of topic appearances commonly found in data from low-income households. From our analyses, we identify and highlight contexts where these strategies yield the most improvements. Our model analysis code is publicly available at https://github.com/Anniejoan/Uplifting-Lower-income-data .

翻译：为解决这一问题，我们构建了翻译后的非英语、地理及社会经济综合提示，并评估其对来自不同国家和收入群体数据的视觉语言模型性能的影响。研究结果表明，地理与社会经济综合提示能提升模型在低收入数据上的性能，并更倾向于检索低收入家庭数据中常见的主题呈现。通过分析，我们识别并强调了这些策略能产生最大改进的情境。我们的模型分析代码已在 https://github.com/Anniejoan/Uplifting-Lower-income-data 公开提供。