← 研踪 PaperTrailarXiv:2611.11833 · v1
Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI
首次提交 2026-11-09 11:50
版本更新 2026-11-09 11:50
雷达观测 2026-11-10 13:18
摘要
Vision-language models (VLMs) could support medical-image interpretation, but their use requires deciding which interpretations to accept and which images to refer to a clinician. We test whether thresholding stated confidence can retain useful coverage while limiting errors among accepted answers, and how this depends on the population. Eight open-weight VLMs, including two reasoning models, assess 3,888 brain MRI slices from post-treatment glioma patients (BraTS 2024) and healthy volunteers (IXI) for tumor or gross abnormality. BraTS labels are mask-derived; IXI slices are treated as negatives. On BraTS, no threshold selects a nonempty set with at most 5% empirical error for any model, even when chosen retrospectively. This also holds for four models evaluated on a large-lesion, distant-negative subset. At a 10% error budget, Gemma-4-12B retains 24.4% of slices and every other model at most 2.5%. To investigate this limited selection ability, we separate confidence differences between predicted answers from differences within each answer. For four models with available outcome-level summaries, pooled mean confidence differs more between answers than between correct and incorrect responses within each answer. A covariance decomposition explains how this pattern can produce opposite confidence-correctness associations across populations. At a 20% error budget, accepting every "tumor" answer covers more slices than any confidence threshold for two models. These findings caution against using unvalidated stated confidence as a standalone deferral signal and support population-specific validation before deployment. Code is available at https://github.com/amir-sbg/VLM-Answer-or-Defer.
作者备注：Accepted to the WACV 2027 FABRIC Workshop
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 11:50 · 最新观测版本
Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI
Vision-language models (VLMs) could support medical-image interpretation, but their use requires deciding which interpretations to accept and which images to refer to a clinician. We test whether thresholding stated confidence can retain useful coverage while limiting errors among accepted answers, and how this depends on the population. Eight open-weight VLMs, including two reasoning models, assess 3,888 brain MRI slices from post-treatment glioma patients (BraTS 2024) and healthy volunteers (IXI) for tumor or gross abnormality. BraTS labels are mask-derived; IXI slices are treated as negatives. On BraTS, no threshold selects a nonempty set with at most 5% empirical error for any model, even when chosen retrospectively. This also holds for four models evaluated on a large-lesion, distant-negative subset. At a 10% error budget, Gemma-4-12B retains 24.4% of slices and every other model at most 2.5%. To investigate this limited selection ability, we separate confidence differences between predicted answers from differences within each answer. For four models with available outcome-level summaries, pooled mean confidence differs more between answers than between correct and incorrect responses within each answer. A covariance decomposition explains how this pattern can produce opposite confidence-correctness associations across populations. At a 20% error budget, accepting every "tumor" answer covers more slices than any confidence threshold for two models. These findings caution against using unvalidated stated confidence as a standalone deferral signal and support population-specific validation before deployment. Code is available at https://github.com/amir-sbg/VLM-Answer-or-Defer.
查看此版本解读 →查看此版本原文 ↗