Claim Verification on AVeriTeC Retrieved (I) (dev)
73.6AccuracyDebateCV
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DebateCVLLMs=Llama-3.1-8B2025.07 | 73.6 | 54.8 | |
| DebateCVLLMs=Qwen-2.5-7B2025.07 | 72.4 | 54.6 | |
| w/o CcorrectLLMs=Llama-3.1-8B2025.07 | 71.6 | 54.2 | |
| w/o CcorrectLLMs=Qwen-2.5-7B2025.07 | 71.2 | 53.8 | |
| InFactLLMs=GPT-4o2025.07 | 68.8 | 52.6 | |
| CooperationLLMs=GPT-4o2025.07 | 68.4 | 52.2 | |
| w/o CerrorLLMs=Llama-3.1-8B2025.07 | 68.2 | 51.8 | |
| HerOLLMs=Llama-3.1-8B2025.07 | 67.8 | 51.8 | |
| InFactLLMs=GPT-4o-Mini2025.07 | 67.4 | 51.4 | |
| MajorityLLMs=GPT-4o2025.07 | 67.2 | 51.6 | |
| HerOLLMs=Qwen-2.5-7B2025.07 | 66.8 | 51.2 | |
| CoTLLMs=GPT-4o2025.07 | 66.6 | 51.4 | |
| w/o CerrorLLMs=Qwen-2.5-7B2025.07 | 66.4 | 51.2 | |
| MajorityLLMs=GPT-4o-Mini2025.07 | 66.2 | 51.4 | |
| CooperationLLMs=GPT-4o-Mini2025.07 | 66.2 | 51.6 | |
| w/o Debate-SFTLLMs=GPT-4o2025.07 | 66.2 | 50.2 | |
| CoTLLMs=GPT-4o-Mini2025.07 | 65.8 | 51 | |
| CoTLLMs=Qwen-2.5-7B2025.07 | 65.4 | 50.6 | |
| InFactLLMs=Qwen-2.5-7B2025.07 | 65.4 | 50.6 | |
| MajorityLLMs=Qwen-2.5-7B2025.07 | 65.4 | 49.8 | |
| InFactLLMs=Llama-3.1-8B2025.07 | 65.2 | 50.4 | |
| MajorityLLMs=Llama-3.1-8B2025.07 | 65.2 | 49.4 | |
| CoTLLMs=Llama-3.1-8B2025.07 | 65 | 50.2 | |
| CooperationLLMs=Llama-3.1-8B2025.07 | 64.8 | 51 | |
| CooperationLLMs=Qwen-2.5-7B2025.07 | 64.4 | 50.6 | |
| w/o Debate-SFTLLMs=GPT-4o-Mini2025.07 | 61.2 | 46.8 | |
| w/o Debate-SFTLLMs=Llama-3.1-8B2025.07 | 56.2 | 43.2 | |
| w/o Debate-SFTLLMs=Qwen-2.5-7B2025.07 | 56 | 42.8 |