放大医疗保健语言模型问答中的差异
Zoom In Disparities in Healthcare LLM Q&A
AI总结：
研究多语言医疗保健问答中LLM的跨语言差异，构建多语言数据集，分析覆盖范围与响应对齐，通过案例研究发现差异显著，非英语维基百科上下文摘录可改善事实对齐，为构建公平多语言医疗AI系统提供途径。
摘要：
将人工智能集成到医疗保健中时，公平获取可靠的健康信息至关重要。然而，信息质量因语言而异，这引发了对多语言大语言模型（LLM）可靠性和一致性的担忧。我们系统地研究了跨语言差异，涉及英语、德语、土耳其语、中文（普通话）和意大利语的多语言医疗保健问答中LLM答案的预训练源和事实对齐情况。我们构建了多语言维基医疗保健数据集，分析跨语言医疗保健覆盖范围，评估LLM响应与这些参考的对齐情况，并通过使用上下文信息和检索增强生成进行事实对齐的案例研究。研究结果揭示了维基百科覆盖范围和LLM事实对齐方面存在显著的跨语言差异。跨LLM，即使提示是非英语的，响应也更符合英语维基百科。在推理时提供非英语维基百科的上下文摘录有效地将事实对齐转向与文化相关的知识。这些结果突出了构建更公平的多语言医疗保健人工智能系统的实用途径。
英文摘要：
Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, raising concerns about the reliability and consistency of multilingual Large Language Models (LLMs). We systematically examine cross-lingual disparities in pre-training source and factuality alignment in LLM answers for multilingual healthcare Q&A across English, German, Turkish, Chinese (Mandarin), and Italian. We (i) constructed Multilingual Wiki Health Care (MultiWikiHealthCare), a multilingual dataset from Wikipedia; (ii) analyzed cross-lingual healthcare coverage; (iii) assessed LLM response alignment with these references; and (iv) conducted a case study on factual alignment through the use of contextual information and Retrieval-Augmented Generation (RAG). Our findings reveal substantial cross-lingual disparities in both Wikipedia coverage and LLM factual alignment. Across LLMs, responses align more with English Wikipedia, even when the prompts are non-English. Providing contextual excerpts from non-English Wikipedia at inference time effectively shifts factual alignment toward culturally relevant knowledge. These results highlight practical pathways for building more equitable, multilingual AI systems for healthcare.
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。
