List your company
ResearchFormerly WizWand

Object Hallucination Detection on Object Hall-Bench

63Res ScoreLLaVA
10.16823.88437.651.316Nov 21, 2024
Updated 5mo ago

Evaluation results

MethodLinks
LLaVAModel Size=13B, Baseline Category=LVLMs2024.116329.5
MuffinModel Size=13B, Baseline Category=LVLMs2024.1150.524.5
POVIDModel Size=7B, Baseline Category=reinforcement learning-based2024.1148.124.4
VCDModel Size=7B, Baseline Category=training-free2024.1147.425.24
ICDModel Size=7B, Baseline Category=training-free2024.1147.425
LLaVA-1.5Model Size=13B, Baseline Category=LVLMs2024.1147.0623.33
LLaVA-1.5Model Size=7B, Baseline Category=LVLMs2024.1146.7125.08
VDD-NoneModel Size=7B, Baseline Category=training-free2024.1146.7125.19
VCDModel Size=13B, Baseline Category=training-free2024.1146.3723.1
ICDModel Size=13B, Baseline Category=training-free2024.1145.5221.93
OPERAModel Size=7B, Baseline Category=training-free2024.1145.122.3
VDD-NoneModel Size=13B, Baseline Category=training-free2024.1144.6422.23
QWEN-VLModel Size=10B, Baseline Category=LVLMs2024.1140.420.7
Less-is-moreModel Size=7B, Baseline Category=training-free2024.1140.317.8
HA-DPOModel Size=7B, Baseline Category=reinforcement learning-based2024.1139.919.9
LLaVA-RLHFModel Size=13B, Baseline Category=reinforcement learning-based2024.1138.118.9
LRVModel Size=7B, Baseline Category=training-free2024.1132.322.3
LLaVA1.5-7B-BPOModel Size=7B, Baseline Category=reinforcement learning-based2024.1131.915.1
LACINGModel Size=7B2024.1127.8614.22
LLaVA1.5-13B-BPOModel Size=13B, Baseline Category=reinforcement learning-based2024.1127.312.9
LACINGModel Size=13B2024.1127.2114.1
RLHF-VModel Size=13B, Baseline Category=reinforcement learning-based2024.1112.27.5