Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

POPE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Object Hallucination EvaluationPOPE
Accuracy94.42
2,056
Object HallucinationPOPE Popular
Accuracy93.33
406
Object HallucinationPOPE Adversarial
Accuracy90
367
Object HallucinationPOPE (Random)
F1 Score93.02
338
Hallucination EvaluationPOPE
Accuracy94.42
281
Object Hallucination EvaluationPOPE
Accuracy92
259
Object Hallucination EvaluationPOPE Adversarial
Accuracy89.8
174
Object Hallucination EvaluationPOPE Random
Accuracy94
152
Object Hallucination EvaluationPOPE
Accuracy (POPE)87.6
137
Visual Question AnsweringPOPE
Accuracy89.6
136
Object Hallucination EvaluationPOPE (test)
Accuracy90.6
123
Multimodal UnderstandingPOPE
POPE Score0.906
116
Object Hallucination EvaluationPOPE MSCOCO
F1 Score93.97
114
Object Hallucination EvaluationPOPE (popular)
Accuracy92
100
Object Hallucination EvaluationPOPE GQA
Accuracy91.03
86
Object Hallucination EvaluationPOPE Adversarial offline
F1 Score68.96
84
Object Hallucination EvaluationPOPE Popular offline
F1 Score84.43
84
Object Hallucination EvaluationPOPE Random offline
F1 Score73.6
84
Object Hallucination EvaluationPOPE A-OKVQA
Accuracy91.2
83
Object HallucinationPOPE
F1 Score91.9
79
Object Hallucination EvaluationPOPE GQA Popular
Accuracy89.4
70
Transfer AttackPOPE (test)
CAE0.2477
69
Object Hallucination EvaluationPOPE
Average Accuracy100.43
53
Object ProbingPOPE Average
Accuracy87.84
52
Object Hallucination EvaluationPOPE Random, Popular, Adversarial v1.0
Random Score94.27
51
Showing 25 of 163 rows