Table Fact Verification on TabFact (dev)
85.1AccuracyREASTAP
Evaluation results
| Method | Links | |
|---|---|---|
| REASTAP2022.10 | 85.1 | |
| TAPEXpre-training_steps=50000, fine-tuning_steps=200002021.07 | 84.6 | |
| TAPEX2022.10 | 84.2 | |
| T5-3BMode=finetune2022.01 | 83.97 | |
| DecompTaPas2022.10 | 82.7 | |
| TableFormer2022.10 | 82 | |
| BART2021.07 | 81.2 | |
| Eisenschlos et al.model_category=Pre-trained Language Models2021.07 | 81 | |
| TaPas2022.10 | 81 | |
| BART2022.10 | 81 | |
| Yang et al.model_category=Pre-trained Language Models2021.07 | 74.9 | |
| GPT-42025.01 | 74.4 | |
| TAMAbackbone=LLaMA 3.1 8B Instruct2025.01 | 73.82 | |
| Zhang et al.model_category=Pre-trained Language Models2021.07 | 73.3 | |
| SAT2022.10 | 73.3 | |
| Shi et al.model_category=Pre-trained Language Models2021.07 | 72.5 | |
| HeterTFV2022.10 | 72.5 | |
| Zhong et al.model_category=Pre-trained Language Models2021.07 | 71.8 | |
| LFC2022.10 | 71.8 | |
| GPT-3.52025.01 | 67.41 | |
| Chen et al.model_category=Pre-trained Language Models2021.07 | 66.1 | |
| LPA-Ranking2022.10 | 65.1 | |
| LLaMA 3.1 8B Instructstatus=base model2025.01 | 58.44 | |
| T0 3BMode=zero-shot2022.01 | 52.45 | |
| Codex 175BFew-shot selection strategy=random2022.01 | 51.58 | |
| GPT-3 175BFew-shot selection strategy=select2022.01 | 51 | |
| Codex 175BFew-shot selection strategy=select2022.01 | 50.97 | |
| GPT-3 175BFew-shot selection strategy=random2022.01 | 49.67 |