领域专用医疗AI刷屏研究被误解：微调后的前沿模型可超越通用模型
英文摘要
The viral study tested medical AI products UpToDate and OpenEvidence—not underlying models—on benchmarks like MedQA and HealthBench, finding them worse than frontier general-purpose models. The author argues this does not prove domain-specific models are inherently inferior; their own comprehensive benchmark shows fine-tuning a frontier model for medicine yields a noticeable boost. Current domain-specific models often lag because they are built on older or weaker open-source base models, not because specialization fails. For example, Baichuan-M4 is cited as a medical-specific model that claims to outperform frontier models. The main takeaway is that adapting strong frontier models into medical tools quickly would produce superior domain-specific systems, but open-source base model progress and adaptation speed remain challenges.
中文摘要
刷屏研究测试了医疗AI产品UpToDate和OpenEvidence（非底层模型），在MedQA、HealthBench等有限基准上表现不如前沿通用模型。作者指出这并不证明领域专用模型天生劣势；其自有综合基准显示将前沿模型针对医学微调可获得显著提升。当前领域专用模型常因基于较旧或较弱的开源模型而落后，并非专精失效。例如百川智能的Baichuan-M4声称医疗专用模型性能超越前沿模型。关键结论是：若能快速将强大的前沿模型适配为医学工具，将诞生更优的领域专用系统，但开源基座模型进步和适配速度仍是瓶颈。
关键要点
The viral study only tested specific products (UpToDate, OpenEvidence) likely built on older models; it does not invalidate the potential of domain-specific models.
刷屏研究仅测试了可能基于较旧模型的具体产品（UpToDate、OpenEvidence），并未否定领域专用模型的潜力。
Author's own benchmark shows fine-tuning a frontier model for medicine reliably improves performance, proving domain adaptation works.
作者自有基准显示将前沿模型微调为医学用途可稳定提升性能，证明领域适配有效。
Current medical-specific models often lag because they are built on non-frontier open-source models, not because specialization is a dead end.
当前医疗专用模型多因基于非前沿开源模型而落后，并非专精路线走不通。
Baichuan-M4 is an example of a medical-specific model that claims to outperform general-purpose frontier models.
百川M4是声称超越通用前沿模型的医疗专用模型案例。
The real bottleneck is the slow pace of open-source base model advancement and slow adaptation into medical tools.
真正的瓶颈是开源基座模型进步缓慢，以及向医疗工具的适配速度滞后。