Fact-checking on HOVER 4-hop (test)
66.23Macro F1Trification
Evaluation Results
| Method | Links | |
|---|---|---|
| TrificationModel Category=Our, Method Components=Full2025.11 | 66.23 | |
| PACARModel Category=III2025.11 | 63.82 | |
| LoCaLModel Category=IV2025.11 | 61.59 | |
| TrificationModel Category=Our, Method Components=w/o REFINE2025.11 | 60.99 | |
| ProgramFCModel Category=III, Number of programs (N)=12025.11 | 59.16 | |
| ChatGPTModel Category=II2025.11 | 58.73 | |
| ProgramFCModel Category=III, Number of programs (N)=52025.11 | 57.74 | |
| CodexModel Category=II2025.11 | 57.27 | |
| SearChainModel Category=IV2025.11 | 56.54 | |
| DeBERTaV3-NLIModel Category=I2025.11 | 56 | |
| Flan-T5Model Category=II2025.11 | 55.42 | |
| TrificationModel Category=Our, Method Components=w/o REFINE and THINK2025.11 | 55.2 | |
| RoBERTa-NLIModel Category=I2025.11 | 52.4 | |
| MUTIVERSModel Category=I2025.11 | 51.86 | |
| LisT5Model Category=I2025.11 | 50.46 | |
| BERT-FCModel Category=I2025.11 | 48.57 |