超越端点增益：医学专业化的权重增量审计
Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization
浏览论文内容
中文总结 AI 辅助
本研究提出配对权重增量路径审计方法，应用于两组通用模型到医学专业模型的检查点对，发现解码器更新与医学基准变动相关，但组件定位不清晰，明确审计仅针对纯文本多项选择题基准变动。
中文摘要 AI 辅助
专业语言模型通常通过端点增益来理解：通用模型得分较低，专业模型得分较高，这一差异被视为专业化的证据，而发布的更新本身却未得到充分检验。我们提出一种配对权重增量路径审计方法，并将其应用于两个公开的对齐通用模型到医学专业模型的检查点对：Gemma-3-4B-IT到MedGemma-4B-IT，以及Qwen2.5-7B-Instruct到HuatuoGPT-o1-7B。在这两个对中，完整解码器侧更新强烈重构了测得的医学基准变动（分别为0.974和1.183的端点归一化保留值），使得每个解码器增量都成为该审计的合适载体。然而，这一变动并未清晰定位：在两个对中，MLP是最强的广泛组件族，但混合的域外变动、10个种子匹配的对照组以及端点锚定的回滚，都阻碍了唯一的粗粒度组件族解释。因此，该审计将更新级重构与组件级解释分离开来，其结论仅涉及纯文本多项选择题基准的变动，不涉及临床验证、修复或电路级机制。
英文摘要
Specialist language models are usually understood through endpoint gains: the generalist scores lower, the specialist scores higher, and the difference is treated as evidence of specialization. This leaves the released update itself largely unexamined. We propose a paired weight-delta path audit and apply it to two public, aligned generalist-to-medical-specialist checkpoint pairs: Gemma-3-4B-IT to MedGemma-4B-IT and Qwen2.5-7B-Instruct to HuatuoGPT-o1-7B. In both pairs, the full decoder-side update strongly reconstructs measured medical benchmark movement (0.974 and 1.183 endpoint-normalized retention), making each decoder delta an appropriate substrate for the audit. Yet the movement is not cleanly localized. MLP is the strongest broad component family in both pairs, but mixed off-domain movements, 10-seed matched controls, and endpoint-anchored rollbacks prevent a unique coarse-family explanation. The audit therefore separates update-level reconstruction from component-level explanation. Its claims concern text-only multiple-choice benchmark movement, not clinical validation, repair, or circuit-level mechanism.
发表机构
- IIT Kanpur（印度理工学院坎普尔分校）
- Oracle Health AI（甲骨文健康人工智能公司）
- MBZUAI（穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。
