Claim Verification on PerplexityAI (test)
82.3Verification ConfidenceDYDECOMP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DYDECOMPAtomicity=2, Decompose Policy=In-Context Example, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 82.3 | 46.4 | |
| DYDECOMPAtomicity=2, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 80.2 | 40 | |
| DYDECOMPAtomicity=1, Decompose Policy=In-Context Example, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 79.1 | 34.7 | |
| DYDECOMPAtomicity=1, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 76.8 | 33.3 | |
| WICEAtomicity=1, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 76.3 | 27.3 | |
| WICEAtomicity=2, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 76.3 | 38.5 | |
| WICEAtomicity=0, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 75.7 | 33.4 | |
| DYDECOMPAtomicity=0, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 75.7 | 32.3 | |
| FActScoreAtomicity=1, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 75.4 | 26 | |
| R-NDAtomicity=2, Decompose Policy=In-Context Example, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 75.1 | 39.2 | |
| R-NDAtomicity=1, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.9 | 23 | |
| FActScoreAtomicity=2, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.9 | 38.5 | |
| FActScore-AtomAtomicity=2, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.8 | 38.5 | |
| R-NDAtomicity=2, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.7 | 38.5 | |
| FActScore-AtomAtomicity=1, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.3 | 24.7 | |
| FActScoreAtomicity=0, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 74.1 | 30.9 | |
| DYDECOMPAtomicity=0, Decompose Policy=In-Context Example, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 73.3 | 30.1 | |
| R-NDAtomicity=0, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 73 | 28.3 | |
| FActScoreAtomicity=2, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70.6 | 69.2 | |
| WICEAtomicity=0, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70.5 | 85.6 | |
| FActScoreAtomicity=0, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70.2 | 84.4 | |
| FActScore-AtomAtomicity=0, Verify Policy=In-Context Example, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70.2 | 19.7 | |
| R-NDAtomicity=0, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70 | 80.2 | |
| WICEAtomicity=2, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 70 | 67.1 | |
| FActScore-AtomAtomicity=2, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 69.5 | 65 | |
| FActScoreAtomicity=1, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 69.4 | 74 | |
| WICEAtomicity=1, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 69 | 76 | |
| DYDECOMPAtomicity=0, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 68.5 | 82 | |
| FActScore-AtomAtomicity=1, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 68.5 | 71.7 | |
| R-NDAtomicity=1, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 68.1 | 67.3 | |
| DYDECOMPAtomicity=1, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 68 | 78 | |
| R-NDAtomicity=2, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 67.5 | 62.2 | |
| DYDECOMPAtomicity=2, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 65.6 | 67.9 | |
| FActScore-AtomAtomicity=0, Verify Policy=Retrieval, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 65.5 | 77 | |
| DYDECOMPAtomicity=1, Decompose Policy=Retrieval, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 65.1 | 75.3 | |
| DYDECOMPAtomicity=2, Decompose Policy=Retrieval, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 63.3 | 66.4 | |
| DYDECOMPAtomicity=0, Decompose Policy=Retrieval, Decomposition LLM=Llama3-Inst-70B, Verification LLM=Llama3-Inst-8B2025.03 | 61.2 | 79.9 | |
| WICEAtomicity=0, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 60 | 55.3 | |
| R-NDAtomicity=0, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 60 | 46.3 | |
| FActScoreAtomicity=2, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 59.4 | 36.4 | |
| FActScoreAtomicity=0, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 59.3 | 52.2 | |
| R-NDAtomicity=1, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 59.1 | 29 | |
| R-NDAtomicity=2, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 58.7 | 38.5 | |
| FActScore-AtomAtomicity=2, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 58.6 | 38.5 | |
| WICEAtomicity=2, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 58.6 | 37.1 | |
| FActScoreAtomicity=1, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 58.3 | 31 | |
| DYDECOMPAtomicity=0, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 58 | 50.7 | |
| DYDECOMPAtomicity=1, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 56.9 | 45.7 | |
| DYDECOMPAtomicity=2, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 56.4 | 38.6 | |
| WICEAtomicity=1, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 56.3 | 34.7 | |
| FActScore-AtomAtomicity=1, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 56.1 | 33.7 | |
| FActScore-AtomAtomicity=0, Verify Policy=No-Context, Decomposition LLM=DeepSeek-V3, Verification LLM=Llama3-Inst-8B2025.03 | 55.7 | 45.4 |