Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909650001068032 |
|---|---|
| author | Oh, Gyutaek Kim, Seoyeon Park, Sangjoon Kim, Byung-Hoon |
| author_facet | Oh, Gyutaek Kim, Seoyeon Park, Sangjoon Kim, Byung-Hoon |
| contents | Test-time scaling has recently emerged as a promising approach for enhancing the reasoning capabilities of large language models or vision-language models during inference. Although a variety of test-time scaling strategies have been proposed, and interest in their application to the medical domain is growing, many critical aspects remain underexplored, including their effectiveness for vision-language models and the identification of optimal strategies for different settings. In this paper, we conduct a comprehensive investigation of test-time scaling in the medical domain. We evaluate its impact on both large language models and vision-language models, considering factors such as model size, inherent model characteristics, and task complexity. Finally, we assess the robustness of these strategies under user-driven factors, such as misleading information embedded in prompts. Our findings offer practical guidelines for the effective use of test-time scaling in medical applications and provide insights into how these strategies can be further refined to meet the reliability and interpretability demands of the medical domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13102 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs Oh, Gyutaek Kim, Seoyeon Park, Sangjoon Kim, Byung-Hoon Computation and Language Artificial Intelligence Computers and Society Test-time scaling has recently emerged as a promising approach for enhancing the reasoning capabilities of large language models or vision-language models during inference. Although a variety of test-time scaling strategies have been proposed, and interest in their application to the medical domain is growing, many critical aspects remain underexplored, including their effectiveness for vision-language models and the identification of optimal strategies for different settings. In this paper, we conduct a comprehensive investigation of test-time scaling in the medical domain. We evaluate its impact on both large language models and vision-language models, considering factors such as model size, inherent model characteristics, and task complexity. Finally, we assess the robustness of these strategies under user-driven factors, such as misleading information embedded in prompts. Our findings offer practical guidelines for the effective use of test-time scaling in medical applications and provide insights into how these strategies can be further refined to meet the reliability and interpretability demands of the medical domain. |
| title | Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2506.13102 |