针对保守文化下生殖健康沟通难题，研究提出适配本地表达的LLM干预框架。
Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts
- 基于临床观察与访谈，提炼出间接沟通的双维特征
- 五款主流LLM在语义漂移和多义词上准确率不足60%
- 为文化敏感型健康对话设计提供可落地的实践建议
低资源国家占全球孕产妇死亡数的90%以上，巴基斯坦2023年贡献近半数。由于多数死亡可预防，大语言模型（LLMs）有望通过自动化健康传播与风险评估缓解危机。然而，在保守语境中，性与生殖健康（SRH）沟通常依赖隐喻与暗示，导致信息模糊，阻碍基于LLM的干预。本研究在巴基斯坦开展两阶段研究：(1) 分析来自临床观察、访谈及焦点小组的资料，揭示沟通中的两个核心维度（指称领域与表达方式）；(2) 评估五款主流LLM在该数据上的解释能力。结果表明，现有模型在处理语义漂移、谣言及多义性方面表现不佳。研究贡献包括：(1) 提炼出SRH沟通的实证主题，(2) 构建间接表达分类框架，(3) 提供LLM性能评估，(4) 提出面向文化情境的通信设计建议。
原文摘要 · Abstract (English)
Low-resource countries represent over 90% of maternal deaths, with Pakistan among the top four countries contributing nearly half in 2023. Since these deaths are mostly preventable, large language models (LLMs) can help address this crisis by automating health communication and risk assessment. However, sexual and reproductive health (SRH) communication in conservative contexts often relies on indirect language that obscures meaning, complicating LLM-based interventions. We conduct a two-stage study in Pakistan: (1) analyzing data from clinical observations, interviews, and focus groups with clinicians and patients, and (2) evaluating the interpretive capabilities of five popular LLMs on this data. Our analysis identifies two axes of communication (referential domain and expression approach) and shows LLMs struggle with semantic drift, myths, and polysemy in clinical interactions. We contribute: (1) empirical themes in SRH communication, (2) a categorization framework for indirect communication, (3) evaluation of LLM performance, and (4) design recommendations for culturally-situated SRH communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。