LogicCheckGPT icon indicating copy to clipboard operation
LogicCheckGPT copied to clipboard

verified publisher icon CRIPAC-DIG
→

Metadata

[ACL 2024] Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinations in LVLMs by itself through logical closed loops.

Results 2 LogicCheckGPT issues
Sort by recently updated
recently updated
newest added

Results cannot be reproduced

2 comment

Hi @Hyperwjf, Thanks for sharing your great work! I am trying to reproduce the results based on LLaVA-1.5-7B on POPE reported in the paper. The reproduced results are as follows:...

Jiahao000 avatar Jiahao000

About baseline

2 comment

A nice work. I would like to ask a question about LURE. LURE needs to mask the object during inference and then correct it. However, POPE and MME are discriminant...

haohaodw avatar haohaodw

← Metadata

21
Stars
1
Forks
Watchers

Owner

verified publisher icon CRIPAC-DIG

Metadata

[ACL 2024] Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinations in LVLMs by itself through logical closed loops.

Back