arXiv Computer Vision
MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language Models
Read the original on arXiv Computer Vision →MYOPIA is a benchmark that evaluates tree-based reasoning in vision‑language models (VLMs) using four human‑refined decision trees for GTSRB, MNIST, CIFAR‑10, and MSCOCO. The study shows that tree traversal consistently underperforms zero‑shot prompting across GPT‑4o, Qwen‑VL Max, and LLaMA‑3.2 11B Vision, with significant gaps between class‑attribute recall and image grounding. Diagnostics reveal that early incorrect decisions and answer extraction losses drive this performance drop, and node‑level analysis links split entropy to lower accuracy.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.