List your company

Claim Verification on AVeriTeC Retrieved (I) (dev)

73.6AccuracyDebateCV
55.29660.04864.869.552Jul 25, 2025

Evaluation results

MethodLinks
DebateCVLLMs=Llama-3.1-8B2025.0773.654.8
DebateCVLLMs=Qwen-2.5-7B2025.0772.454.6
w/o CcorrectLLMs=Llama-3.1-8B2025.0771.654.2
w/o CcorrectLLMs=Qwen-2.5-7B2025.0771.253.8
InFactLLMs=GPT-4o2025.0768.852.6
CooperationLLMs=GPT-4o2025.0768.452.2
w/o CerrorLLMs=Llama-3.1-8B2025.0768.251.8
HerOLLMs=Llama-3.1-8B2025.0767.851.8
InFactLLMs=GPT-4o-Mini2025.0767.451.4
MajorityLLMs=GPT-4o2025.0767.251.6
HerOLLMs=Qwen-2.5-7B2025.0766.851.2
CoTLLMs=GPT-4o2025.0766.651.4
w/o CerrorLLMs=Qwen-2.5-7B2025.0766.451.2
MajorityLLMs=GPT-4o-Mini2025.0766.251.4
CooperationLLMs=GPT-4o-Mini2025.0766.251.6
w/o Debate-SFTLLMs=GPT-4o2025.0766.250.2
CoTLLMs=GPT-4o-Mini2025.0765.851
CoTLLMs=Qwen-2.5-7B2025.0765.450.6
InFactLLMs=Qwen-2.5-7B2025.0765.450.6
MajorityLLMs=Qwen-2.5-7B2025.0765.449.8
InFactLLMs=Llama-3.1-8B2025.0765.250.4
MajorityLLMs=Llama-3.1-8B2025.0765.249.4
CoTLLMs=Llama-3.1-8B2025.076550.2
CooperationLLMs=Llama-3.1-8B2025.0764.851
CooperationLLMs=Qwen-2.5-7B2025.0764.450.6
w/o Debate-SFTLLMs=GPT-4o-Mini2025.0761.246.8
w/o Debate-SFTLLMs=Llama-3.1-8B2025.0756.243.2
w/o Debate-SFTLLMs=Qwen-2.5-7B2025.075642.8