אי-תואמות חזותיות אינן תואמות חזרה: תכנון זיכוי נמרץ ללמידת רפלקסיה מודאלית

תקציר מקורי באנגליתarXiv:2609.36572v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on visual evidence. Yet relying on the image does not guarantee that visual claims are supported by it. Before RL training, 27.81% of the correctly answered responses of Qwen2.5-VL-7B on four multimodal reasoning benchmarks contain at least one direct visual claim that the image does not support. Since outcome-level RL rewards each response as a whole, these claims inherit the positive credit of the correct answer. We introduce a fixed-rollout counterfactual diagnostic that re-scores the same response under an intervened image to separate Evidence-Function Sensitiv