Benchmark RadarAI BENCHMARK PROFILE
TreeProbe
TreeProbe is a dataset of 4,719 expert-adjudicated items covering 467 diseases and 10 subtasks across the Tibetan Tree of Medicine framework, used to evaluate cultural bias in LLMs.
- Released
- 2026-08-01
- Readiness
- Inspectable
- Primary field
- Health & Life Sciences
Why it matters
It addresses the lack of quantitative tools for assessing cultural bias in Tibetan medicine, offering a diagnostic lens for epistemic fairness in medical AI, though it primarily supports the paper's analysis.
Motivation
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.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.