ChatGPT 3.5 with LAPDoc Prompt (SpatialFormat)

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Visual Question Answering (VQA)onDocVQA
ANLS· 2024-02-15
79.8
SOTA
LAPDoc: Layout-Aware Prompting for Documents arXiv:2402.09841
Visual Question Answering (VQA)onInfographicVQA
ANLS· 2024-02-15
54.9
best: 80.3 (Gemini Ultra (pixel only))
LAPDoc: Layout-Aware Prompting for Documents arXiv:2402.09841