Envision, Attend, Then Respond: Counterfactual Hallucination Mitigation in Large Vision-Language Models
Open paper
Benchmark
Model
Rank
Results
object-hallucination-evaluation-on-pope
EnAR (InternVL3.5-8B)
#5
F1: 89.0
visual-question-answering-vqa-on-hallusionbench-average-accuracy
EnAR (Qwen2.5VL-7B)
#18
Accuracy: 56.82
Rank counts only results with a code link.