List your company

Hallucination Assessment on HallusionBench

71.6Answer Accuracy (aAcc)ResDec
33.983243.749153.51563.2809Jan 24, 2026Jan 25, 2026Jan 27, 2026Jan 28, 2026Jan 30, 2026Jan 31, 2026Feb 2, 2026

Evaluation results

MethodLinks
ResDecBackbone=Qwen2.5-VL, Max New Tokens=1282026.0271.64947.1——
DefenderIteration=32026.0169.19————
RegularBackbone=Qwen2.5-VL, Max New Tokens=1282026.0269.145.843.4——
OPERABackbone=Qwen2.5-VL, Max New Tokens=1282026.0268.743.441.5——
VCDBackbone=Qwen2.5-VL, Max New Tokens=1282026.0268.741.339.8——
Liu et al.Augmentation=Insert2026.0168.45————
Yang et al.2026.0168.35————
DefenderIteration=22026.0168.24————
Ablation (Clean Data)2026.0167.93————
DefenderIteration=12026.0167.82————
Liu et al.Augmentation=Add2026.0167.61————
Liu et al.Augmentation=All2026.0167.61————
ICDBackbone=Qwen2.5-VL, Max New Tokens=1282026.0267.639.838.7——
Base (M def (0))2026.0167.51————
DoLaBackbone=Qwen2.5-VL, Max New Tokens=1282026.0266.939.540.8——
MM-EurekaClueTracer=true2026.0265.133.4147.1156.98—
Ocean-R1ClueTracer=true2026.0263.5130.1143.3554.88—
ORSTA-R1ClueTracer=true2026.0260.0527.9136.7153.49—
R1-OneVisionClueTracer=true2026.0258.924.1840.1754.42—
MM-EurekaClueTracer=false2026.0258.4623.0731.549.3—
ORSTA-R1ClueTracer=false2026.0255.4521.7628.6145.81—
Ocean-R1ClueTracer=false2026.0248.8919.3427.7640—
ResDecBackbone=InstructBLIP, Max New Tokens=1282026.0246.510.211.3——
AGLABackbone=InstructBLIP, Max New Tokens=1282026.0245.99.29.7——
RegularBackbone=InstructBLIP, Max New Tokens=1282026.0245.39.510.1——
ResDecBackbone=LLaVA-1.5, Max New Tokens=1282026.0245.112.718.2——
DoLaBackbone=InstructBLIP, Max New Tokens=1282026.0243.88.68.4——
VCDBackbone=InstructBLIP, Max New Tokens=1282026.0243.38.58.1——
AGLABackbone=LLaVA-1.5, Max New Tokens=1282026.0242.98.317.2——
ONLYBackbone=LLaVA-1.5, Max New Tokens=1282026.0242.79.317.5——
MemVRBackbone=LLaVA-1.5, Max New Tokens=1282026.0242.5917.9——
OPERABackbone=InstructBLIP, Max New Tokens=1282026.0242.38.29.7——
RegularBackbone=LLaVA-1.5, Max New Tokens=1282026.0241.58.117.9——
DoLaBackbone=LLaVA-1.5, Max New Tokens=1282026.0241.59.315.7——
OPERABackbone=LLaVA-1.5, Max New Tokens=1282026.0241.25.516.2——
VCDBackbone=LLaVA-1.5, Max New Tokens=1282026.0241.111.413.9——
ICDBackbone=InstructBLIP, Max New Tokens=1282026.02417.57.2——
ICDBackbone=LLaVA-1.5, Max New Tokens=1282026.0238.28.413.9——
R1-OneVisionClueTracer=false2026.0235.438.5712.4331.86—
ACPOModel Scale=14B, Base Model=InternVL32026.03————70
ACPOModel Scale=8B, Base Model=InternVL32026.03————69.1
BAGELModel Category=Unified Models2026.04————52.5
DPOModel Scale=14B, Base Model=InternVL32026.03————69.7
DPOModel Scale=8B, Base Model=InternVL32026.03————67
DPO-ShiftModel Scale=14B, Base Model=InternVL32026.03————70
DPO-ShiftModel Scale=8B, Base Model=InternVL32026.03————65.2
InstructModel Scale=14B, Base Model=InternVL32026.03————68.9
InstructModel Scale=8B, Base Model=InternVL32026.03————66.8
InternVL-UModel Category=Unified Models2026.04————44.8
IPOModel Scale=14B, Base Model=InternVL32026.03————69.8
IPOModel Scale=8B, Base Model=InternVL32026.03————62.8
LLaDA-oModel Category=Unified Models2026.04————47.4
LLaDA-VModel Category=Specialist VLMs2026.04————39.2
LLaDA2.0-UniModel Category=Unified Models2026.04————50.2
Lumina-DiMOOModel Category=Unified Models2026.04————32.9
Qwen2.5-VL-7BModel Category=Specialist VLMs2026.04————51.9
SimPOModel Scale=14B, Base Model=InternVL32026.03————68
SimPOModel Scale=8B, Base Model=InternVL32026.03————66.1
β-DPOModel Scale=14B, Base Model=InternVL32026.03————69.5
β-DPOModel Scale=8B, Base Model=InternVL32026.03————65.7