TableQA on TabFact small (test)
90.4AccuracyTabLaP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TabLaPCategory=Ours, Backbone=GPT-4o mini2024.10 | 90.4 | 90 | |
| NumSolverCategory=Ours, Backbone=GPT-4o mini2024.10 | 89 | — | |
| GPT-4o miniCategory=Zero-shot LLMs2024.10 | 88.6 | — | |
| Chain-of-TableCategory=Few-shot LLMs2024.10 | 86.6 | — | |
| DATERCategory=Few-shot LLMs2024.10 | 85.6 | — | |
| OmniTab-LargeCategory=Fine-tuned PLMs2024.10 | 85.2 | — | |
| GPT-3.5 TurboCategory=Zero-shot LLMs2024.10 | 82.5 | — | |
| TAPEX-LargeCategory=Fine-tuned PLMs2024.10 | 75.3 | — |