发表机构
University of Electronic Science and Technology of China; Tibet University; Peking University; Southwest Jiaotong University（电子科技大学; 西藏大学; 北京大学; 西南交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对大型语言模型的藏医药文化偏见问题，构建了首个基于藏医药“医学之树”框架的基准测试集TreeProbe，发现现有模型存在系统性本体漂移，为公平医疗AI开发提供了诊断基准。
AI 中文摘要
大型语言模型正被视为缓解全球健康不平等的潜在手段，但其输出往往反映占主导地位的高资源医学传统，对传统医学知识体系的覆盖有限。藏医药作为世界四大传统医学体系之一，拥有独立且高度结构化的理论框架。当模型缺乏对藏医药的扎实理解时，可能会依赖主导的认知体系，在推理过程中扭曲本土知识结构。然而，目前几乎没有用于评估藏医药文化偏见的量化工具。为解决这一缺口，我们推出TreeProbe——首个围绕藏医药本土“医学之树”框架构建的文化偏见基准测试集，包含4719项经专家裁定的条目，覆盖467种疾病及“三根”维度下的10个子任务。对代表性大型语言模型的实验显示，当前模型在本土藏医药语境下仍存在局限，表现出系统性的外部本体漂移。进一步分析表明，模型漂移方向要么偏向生物医学推理，要么偏向中医推理，这由预训练数据构成及中医与藏医药的表面相似性所决定。TreeProbe为开发兼具语言包容性与认知公平性的医疗人工智能系统提供了诊断基准，代码与数据可在匿名仓库获取：https://www.anonymous-repo.com
英文摘要
Large language models are increasingly viewed as a potential means of mitigating global health inequities, yet their outputs often reflect dominant high-resource medical traditions and provide limited coverage of traditional medical knowledge systems. Tibetan medicine, one of the world's four major traditional medical systems, has an independent and highly structured theoretical framework. When models lack grounded understanding of Tibetan medicine, they may fall back on dominant epistemic systems and distort the native knowledge structure during reasoning. However, quantitative tools for evaluating cultural bias in Tibetan medicine remain largely absent. To address this gap, we introduce TreeProbe, the first cultural-bias benchmark organized around the native Tree of Medicine framework in Tibetan medicine. It contains 4,719 expert-adjudicated items covering 467 diseases and 10 subtasks along the three roots. Experiments on representative LLMs show that current models remain limited in native Tibetan medical contexts and exhibit systematic external ontology drift. Further analysis reveals that models diverge in whether they drift toward biomedical or TCM reasoning, shaped by pretraining data composition and surface resemblance between TCM and Tibetan medicine. TreeProbe provides a diagnostic benchmark for developing medical AI systems that are both linguistically inclusive and epistemically fair. Code and data are available in an anonymous repository at https://anonymous.4open.science/r/TreeProbe/.
