MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
This addresses the need for reliable deployment of video generative models by providing a missing evaluation benchmark for reasoning coherence, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating reasoning coherence in video generative models by introducing MME-CoF-Pro, a benchmark with 303 samples across 16 categories, and found that models exhibit weak reasoning coherence, with text hints boosting correctness but causing inconsistencies and visual hints aiding structured tasks but struggling with fine-grained perception.
Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To bridge the gap in literature for missing reasoning coherence evaluation, we propose MME-CoF-Pro, a comprehensive video reasoning benchmark to assess reasoning coherence in video models. Specifically, MME-CoF-Pro contains 303 samples across 16 categories, ranging from visual logical to scientific reasoning. It introduces Reasoning Score as evaluation metric for assessing process-level necessary intermediate reasoning steps, and includes three evaluation settings, (a) no hint (b) text hint and (c) visual hint, enabling a controlled investigation into the underlying mechanisms of reasoning hint guidance. Evaluation results in 7 open and closed-source video models reveals insights including: (1) Video generative models exhibit weak reasoning coherence, decoupled from generation quality. (2) Text hints boost apparent correctness but often cause inconsistency and hallucinated reasoning (3) Visual hints benefit structured perceptual tasks but struggle with fine-grained perception. Website: https://video-reasoning-coherence.github.io/