arXiv:2611.13596 · v1
Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics
摘要
Vision-language models (VLMs) are increasingly used as automated judges for multimodal and embodied tasks, yet aggregate accuracy or consistency alone does not reveal whether a judge changes its verdict for the right reason. We propose State-Conditional Invariance (SCI), a reliability principle requiring a judge to remain stable under semantics-preserving changes in presentation while responding to causal interventions that change the task outcome. We instantiate SCI in GridWM-Judge, a simulator-grounded diagnostic benchmark built from deterministic MiniGrid trajectories with aligned Full, evidence-removal, and counterfactual variants, plus presentation and representation probes. Across five diagnostic tasks, GridWM-Judge tests local perception, action-conditioned transitions, presentation stability, representation exchangeability, and Full-CF causal discrimination. Our diagnostic evaluations reveal heterogeneous failure modes, including sensitivity to evidence presentation and encoding, low activation on successful trajectories, and weak paired counterfactual discrimination. Perception-controlled analyses further indicate that visual grounding and objective recovery are substantial, model-dependent bottlenecks. These results motivate jointly reporting correctness, presentation stability, and causal sensitivity instead of relying on a single score.
作者备注：Accepted to NeurIPS 2026 (Track on Evaluations and Datasets). 47 pages, 16 figures. Project page: https://xinyuw922-pixel.github.io/Towards-Reliable-VLM-Judge/ ; Code: https://github.com/xinyuw922-pixel/Towards-Reliable-VLM-Judge ; Data: https://huggingface.co/datasets/nahco318/Towards-Reliable-VLM-Judges