Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Dong, G., Hong, Z., Zhou, X., Yu, Z., Liu, B., Liu, K., Liu, C., Fu, R., & Hou, Y. (2026). Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation. https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation
MLA 9
Dong, Guangyuan, et al. "Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation." https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation.
Chicago (author–date)
Dong, Guangyuan, Ziwei Hong, Xuehao Zhou, Zidong Yu, Bingchen Liu, Kehan Liu, Chuang Liu, Rong Fu, and Yuchao Hou. 2026. "Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation." https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation.
Harvard
Dong, G., Hong, Z., Zhou, X., Yu, Z., Liu, B., Liu, K., Liu, C., Fu, R. and Hou, Y. (2026) 'Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation', Available at: https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation.
Vancouver
Dong G, Hong Z, Zhou X, Yu Z, Liu B, Liu K, et al. Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation. https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation
IEEE
G. Dong, Z. Hong, X. Zhou, Z. Yu, B. Liu, K. Liu, C. Liu, R. Fu, and Y. Hou, "Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation," https://omanscience.com/en/articles/conditional-rank-allocation-for-taxonomy-aware-medical-language-model-adaptation.