SOURCE-LINKED INTELLIGENCE

Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within individual examples. We study answer-level reliability along five-step, question-conditioned evidence-loss trajectories. Using a frozen Qwen2.5-VL-3B-Instruct model, we construct 176 accepted GQA-derived trajectories (880 masking conditions) by progressively masking scene-graph-localized question-critical regions. Native sequence confidence has an evidence monotonicity violation rate (EMVR) of 0.436, and 92.0% of trajectories contain at least one adja

Read original source ↗ Open in workspace

recordType

paper

region

Global