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

Object Hallucination on POPE (Random/Popular/Adversarial Metrics)

91.5F1 Score (Random)

Qwen2.5-VL-3B + P2-DPO

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2.5-VL-3B + P2-DPO 2026.06		91.5	-	-	88.48	-	86.88	88.95
Qwen2.5-VL-3B + DPORLHF-V 2026.06		90.4	-	-	88.59	-	86.41	88.46
LLaVA-1.5-7B + HA-DPO 2026.06		90.25	-	-	87.81	-	82.54	86.86
RC-DPO 2026.05		90.07	90.73	88.03	87.55	86	85.73	-
Qwen2.5-VL-7B + P2-DPO 2026.06		90.05	-	-	87.79	-	86.79	88.21
LLaVA-1.5-7B + V-DPORLHF-V 2026.06		89.9	-	-	87.91	-	84.05	87.28
LLaVA-1.5-7B + P2-DPO 2026.06		89.87	-	-	87.91	-	84.53	87.44
Qwen2.5-VL-3B 2026.06		89.79	-	-	88.05	-	86.26	88.03
Qwen2.5-VL-7B + DPORLHF-V 2026.06		89.72	-	-	86.81	-	84.99	87.17
LLaVA-1.5-7B + V-DPOSAD 2026.06		89.57	-	-	87.62	-	83.77	86.98
LLaVA-1.5-7B 2026.06		89.12	-	-	84.36	-	81.8	85.1
LLaVA-1.5-7B + DPORLHF-V 2026.06		89.12	-	-	85.94	-	84.03	86.38
Qwen2.5-VL-7B 2026.06		89.01	-	-	86.78	-	84.92	86.9
OPA-DPO 2026.05		88.09	89.23	87.4	86.33	86.13	85.16	-
SID 2026.05		87.66	88.87	86.97	85.8	86.1	85.06	-
VCD 2026.05		87.23	88.57	86.97	85.74	86.07	84.87	-
LLaVA-1.5-7B + VCD 2026.06		87.16	-	-	85.06	-	81.33	84.51
Vanilla 2026.05		86.98	88.37	86.73	85.41	85.73	84.48	-
RLAIF-V 2026.05		86.34	87.9	86.73	85.22	85.4	83.97	-
RC-DPO 2026.05		86.2	87.63	86	84.46	84.87	83.41	-
OPA-DPO 2026.05		85.53	87.27	85.87	84.19	85.2	83.57	-
SID 2026.05		84.86	86.77	85.73	83.9	84.53	82.63	-
VCD 2026.05		84.38	86.4	85.47	83.51	84.37	82.41	-
Vanilla 2026.05		83.52	85.77	84.73	82.52	84.2	82.02	-
RLAIF-V 2026.05		81.78	84.53	83.63	80.86	82.93	80.2	-