List your company

Uncertainty Quantification on OKVQA

79.9AUROCVSE
50.7858.3465.973.46May 26, 2026May 31, 2026Jun 6, 2026Jun 12, 2026Jun 18, 2026Jun 24, 2026Jun 30, 2026

Evaluation results

MethodLinks
VSECategory=Entropy, Venue=Ours, Model=Qwen32026.0679.9—
SECategory=Entropy, Venue=ICLR’23, Model=Qwen32026.0679—
SCG-PrCategory=Consistency, Venue=EMNLP’23, Model=Qwen2.52026.0676.7—
VSECategory=Entropy, Venue=Ours, Model=Qwen2.52026.0676.7—
SECategory=Entropy, Venue=ICLR’23, Model=Qwen2.52026.0675.8—
SNNECategory=Entropy, Venue=ACL’25, Model=Qwen2.52026.0675.1—
VSECategory=Entropy, Venue=Ours, Model=LLaVA2026.0674.9—
KLECategory=Entropy, Venue=NIPS’25, Model=Qwen2.52026.0674.4—
C&UCategory=Consistency, Venue=CVPR’24, Model=Qwen2.52026.0674.2—
VL-UCategory=Entropy, Venue=arxiv, Model=Qwen2.52026.0673.1—
VL-UCategory=Entropy, Venue=arxiv, Model=Qwen32026.0673.1—
AvgEntCategory=Logit, Venue=EMNLP’24, Model=LLaVA2026.0672.9—
MaxEntCategory=Logit, Venue=EMNLP’24, Model=LLaVA2026.0672.4—
KLECategory=Entropy, Venue=NIPS’25, Model=Qwen32026.0672.4—
C&UCategory=Consistency, Venue=CVPR’24, Model=LLaVA2026.0671.8—
MaxEntCategory=Logit, Venue=EMNLP’24, Model=Qwen32026.0671.5—
VSECategory=Entropy, Venue=Ours, Model=Gemma32026.0671.5—
MaxEntCategory=Logit, Venue=EMNLP’24, Model=Qwen2.52026.0671.4—
SCG-NLICategory=Consistency, Venue=EMNLP’23, Model=Qwen2.52026.0671.4—
SNNECategory=Entropy, Venue=ACL’25, Model=Qwen32026.0671.1—
AvgProbCategory=Logit, Venue=EMNLP’24, Model=LLaVA2026.0670.5—
AvgEntCategory=Logit, Venue=EMNLP’24, Model=Qwen32026.0670.3—
SECategory=Entropy, Venue=ICLR’23, Model=Gemma32026.0670.3—
VL-UCategory=Entropy, Venue=arxiv, Model=Gemma32026.0670.2—
SNNECategory=Entropy, Venue=ACL’25, Model=LLaVA2026.0669.8—
VL-UCategory=Entropy, Venue=arxiv, Model=LLaVA2026.0669.5—
C&UCategory=Consistency, Venue=CVPR’24, Model=Qwen32026.0669.3—
KLEUncertainty Level=Semantic-Level2026.0569.17.7
AvgEntCategory=Logit, Venue=EMNLP’24, Model=Qwen2.52026.0669—
SECategory=Entropy, Venue=ICLR’23, Model=LLaVA2026.0668.5—
AvgProbCategory=Logit, Venue=EMNLP’24, Model=Qwen32026.0667.9—
C&UCategory=Consistency, Venue=CVPR’24, Model=Gemma32026.0667.8—
SCG-PrCategory=Consistency, Venue=EMNLP’23, Model=LLaVA2026.0667.5—
KLECategory=Entropy, Venue=NIPS’25, Model=Gemma32026.0667.3—
KLECategory=Entropy, Venue=NIPS’25, Model=LLaVA2026.0667.2—
SEUncertainty Level=Semantic-Level2026.0566.97.8
SNNECategory=Entropy, Venue=ACL’25, Model=Gemma32026.0666.7—
Verb-UCategory=Verbalized, Venue=NAACL’24, Model=Qwen2.52026.0666.3—
SCG-NLICategory=Consistency, Venue=EMNLP’23, Model=LLaVA2026.0665.8—
SCG-PrCategory=Consistency, Venue=EMNLP’23, Model=Gemma32026.0665.7—
SCG-PrCategory=Consistency, Venue=EMNLP’23, Model=Qwen32026.0665.7—
VIG-TUQUncertainty Level=Token-Level2026.0565.510.4
AvgProbCategory=Logit, Venue=EMNLP’24, Model=Qwen2.52026.0665.3—
VIG-TUQ-AUncertainty Level=Token-Level2026.0564.910.4
Verb-UCategory=Verbalized, Venue=NAACL’24, Model=Gemma32026.0664.7—
VIG-TUQ-JSDUncertainty Level=Token-Level2026.0563.312.1
Token-EntropyUncertainty Level=Token-Level2026.0562.911.4
CCPUncertainty Level=Token-Level2026.0562.811.9
Log-PerplexityUncertainty Level=Token-Level2026.0562.511.7
Max-ProbUncertainty Level=Token-Level2026.0562.312.6
SCG-NLICategory=Consistency, Venue=EMNLP’23, Model=Qwen32026.0659.7—
Verb-UCategory=Verbalized, Venue=NAACL’24, Model=Qwen32026.0659.3—
Token-SarUncertainty Level=Token-Level2026.0559.213.9
SCG-NLICategory=Consistency, Venue=EMNLP’23, Model=Gemma32026.0658.4—
AvgEntCategory=Logit, Venue=EMNLP’24, Model=Gemma32026.0657.7—
AvgProbCategory=Logit, Venue=EMNLP’24, Model=Gemma32026.0657—
MaxEntCategory=Logit, Venue=EMNLP’24, Model=Gemma32026.0656.7—
MaxProbCategory=Logit, Venue=EMNLP’24, Model=Qwen32026.0656.5—
MaxProbCategory=Logit, Venue=EMNLP’24, Model=Gemma32026.0655.5—
MaxProbCategory=Logit, Venue=EMNLP’24, Model=LLaVA2026.0654.2—
Verb-UCategory=Verbalized, Venue=NAACL’24, Model=LLaVA2026.0653.2—
MaxProbCategory=Logit, Venue=EMNLP’24, Model=Qwen2.52026.0651.9—