Prophet

Reported on 3 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 Processing3 results

Visual Question Answering (VQA)onA-OKVQA
MC Accuracy· 2023-03-03
75.1
best: 83.75 (SMoLA-PaLI-X Specialist Model)
SOTA
Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering arXiv:2303.01903
Visual Question Answering (VQA)onA-OKVQA
DA VQA Score· 2023-03-03
58.5
best: 70.55 (SMoLA-PaLI-X Specialist Model)
Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering arXiv:2303.01903
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2023-03-03
62.5
best: 66.8 (PaLI-X-VPD)
Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering arXiv:2303.01903