Claim Verification on HOVER 2-hop
76.69AccuracyInfoRE + CoT
Evaluation Results
| Method | Links | |
|---|---|---|
| InfoRE + CoTBackbone=GPT-4, Zero-shot=true2024.04 | 76.69 | |
| InfoREBackbone=GPT-4, Zero-shot=true2024.04 | 75.87 | |
| CoTBackbone=GPT-4, Zero-shot=true2024.04 | 73.82 | |
| StandardBackbone=GPT-4, Zero-shot=true2024.04 | 72.4 | |
| InfoRE + CoTBackbone=GPT-3.5, Zero-shot=true2024.04 | 69.02 | |
| InfoREBackbone=GPT-3.5, Zero-shot=true2024.04 | 68.21 | |
| CoTBackbone=GPT-3.5, Zero-shot=true2024.04 | 66.7 | |
| StandardBackbone=GPT-3.5, Zero-shot=true2024.04 | 64.74 | |
| InfoRE + CoTBackbone=LLAMA2-70B, Zero-shot=true2024.04 | 53.2 | |
| InfoREBackbone=LLAMA2-70B, Zero-shot=true2024.04 | 52.83 | |
| CoTBackbone=LLAMA2-70B, Zero-shot=true2024.04 | 50.02 | |
| StandardBackbone=LLAMA2-70B, Zero-shot=true2024.04 | 49.41 |