DePlot + GPT-4

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Other3 results

Factual Inconsistency Detection in Chart CaptioningonCHOCOLATE-LVLM
Kendall's Tau-c· 2022-12-20
0.129
best: 0.178 (ChartVE)
SOTA
DePlot: One-shot visual language reasoning by plot-to-table translation arXiv:2212.10505
Factual Inconsistency Detection in Chart CaptioningonCHOCOLATE-FT
Kendall's Tau-c· 2022-12-20
0.109
best: 0.291 (Bard (before Gemini))
SOTA
DePlot: One-shot visual language reasoning by plot-to-table translation arXiv:2212.10505
Factual Inconsistency Detection in Chart CaptioningonCHOCOLATE-LLM
Kendall's Tau-c· 2022-12-20
0.117
best: 0.205 (GPT-4V)
SOTA
DePlot: One-shot visual language reasoning by plot-to-table translation arXiv:2212.10505