Claim Verification on AVeriTeC Golden (dev)
83.4AccuracyDebateCV
Evaluation Results
| Method | Links | |
|---|---|---|
| DebateCVLLMs=Llama-3.1-8B2025.07 | 83.4 | |
| DebateCVLLMs=Qwen-2.5-7B2025.07 | 82 | |
| MajorityLLMs=GPT-4o2025.07 | 81.8 | |
| CooperationLLMs=GPT-4o2025.07 | 81.8 | |
| CoTLLMs=GPT-4o2025.07 | 81.6 | |
| CooperationLLMs=GPT-4o-Mini2025.07 | 81.6 | |
| MajorityLLMs=GPT-4o-Mini2025.07 | 81.4 | |
| InFactLLMs=GPT-4o2025.07 | 81.2 | |
| CoTLLMs=GPT-4o-Mini2025.07 | 80.8 | |
| HerOLLMs=Llama-3.1-8B2025.07 | 80.4 | |
| HerOLLMs=Qwen-2.5-7B2025.07 | 80 | |
| InFactLLMs=GPT-4o-Mini2025.07 | 79.2 | |
| w/o Debate-SFTLLMs=GPT-4o2025.07 | 78.8 | |
| MajorityLLMs=Llama-3.1-8B2025.07 | 78 | |
| MajorityLLMs=Qwen-2.5-7B2025.07 | 77.6 | |
| CooperationLLMs=Qwen-2.5-7B2025.07 | 77.4 | |
| CoTLLMs=Qwen-2.5-7B2025.07 | 77 | |
| CoTLLMs=Llama-3.1-8B2025.07 | 76.8 | |
| w/o CcorrectLLMs=Llama-3.1-8B2025.07 | 76.8 | |
| CooperationLLMs=Llama-3.1-8B2025.07 | 76.6 | |
| w/o CerrorLLMs=Llama-3.1-8B2025.07 | 76.4 | |
| w/o CerrorLLMs=Qwen-2.5-7B2025.07 | 75.8 | |
| w/o CcorrectLLMs=Qwen-2.5-7B2025.07 | 75.6 | |
| w/o Debate-SFTLLMs=GPT-4o-Mini2025.07 | 74.6 | |
| InFactLLMs=Qwen-2.5-7B2025.07 | 74.4 | |
| InFactLLMs=Llama-3.1-8B2025.07 | 73.2 | |
| w/o Debate-SFTLLMs=Llama-3.1-8B2025.07 | 66.6 | |
| w/o Debate-SFTLLMs=Qwen-2.5-7B2025.07 | 61.4 |