ARBOR：按问题分配秩的医学问答微调方法
Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
给医学问答做了个按问题动态分配 LoRA 秩的微调方法，在 Qwen3-8B 上比 LoRA r16 高了 1 个多百分点，专科越多优势越大，做医疗方向微调的可以看看。
论文提出 ARBOR，一种参数高效微调方法，通过加性门控从共享低秩基中选择秩一组件，结合问题表示、专科标签和临床操作标签进行条件路由。在 Qwen3-8B 上于 CMB、CMExam、MedQA、MedMCQA 四个基准测试，五种子实验平均准确率 69.69%，比 LoRA r16 和 MoELoRA 分别高 1.26 和 1.30 个百分点。训练专科从 1 个扩展到 7 个时，相对 LoRA r16 的优势从 0.08 点增至 1.94 点。原子聚类与专科标签的调整兰德指数为 0.62，支持临床路由机制的有效性。
Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method that selects rank-one components from a shared low-rank basis for each question. An additive gate combines question representations, specialty tags, operation tags, and their interaction; a learned coefficient scales the adapter residual. An illustrative separation under orthogonal, equiprobable subtasks shows how conditional selection can avoid an approximation floor faced by a fixed update with the same active rank. This result motivates the design without asserting a corresponding bound for medical corpora. On Qwen3-8B across CMB, CMExam, MedQA, and MedMCQA, five-seed experiments yield 69.69% mean accuracy across benchmarks, exceeding LoRA r16 and MoELoRA by 1.26 and 1.30 percentage points, respectively. The reported advantage over LoRA r16 increases from 0.08 to 1.94 points as training expands from one to seven specialties. Tag perturbations and atom masking support the usefulness of clinical routing, while atom clusters align with the supplied specialty labels (adjusted Rand index 0.62). Calibration, transfer, and measured costs further characterize the method. These findings support structured conditional adaptation for medical QA, while leaving clinical safety and broader deployment untested.
