SOURCE-LINKED INTELLIGENCE

Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal little about how different information sources shape the generation process. We propose a causal and temporal evaluation framework that traces the evolving roles of visual input, question text, and generated prefixes during autoregressive decoding. Grounded in a Structural Causal Model, we use interventions and backdoor adjustment to derive three step-indexed causal-drive metrics---Visual Causal Drive (VCD), Question

Read original source ↗ Open in workspace

recordType

paper

region

Global