Research
Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models
arXiv:2609.06419v1 Announce Type: new Abstract: Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based m
arXiv:2609.06419v1 Announce Type: new Abstract: Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based methods optimize verbalized confidence together with answer generation. However, this joint optimization may interfere with answer learning and drive confidence toward near-binary values. Verbalized confidence also provides no explicit assessment of visual support. We therefore separate capability learning from confidence estimation and propose extbf{DualRead}. DualRead builds on the insight that reliability can be read from the actor's internal states at critical moments in the answering process. It freezes the GRPO-trained actor and combines pre-answer solvability with a post-answer assessment of the generated answer and its visual support. To further assess whether confidence reflects visual grounding, we introduce extbf{Counterfactual Confidence Grounding AUC} (CCG-AUC). It measures whether confidence decreases when real-image substitution changes the actor from correct to incorrect. Across two VLM backbones and both in- and out-of-distribution medical VQA benchmarks, DualRead improves correctness discrimination and calibration over verbalized confidence while preserving answer accuracy. CCG-AUC reveals whether confidence responds to answer-relevant visual evidence rather than primarily to non-visual cues.
Related
- H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning
- Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning
- MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data
- Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs
- Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models
Source: arXiv cs.CV | 2026-09-09