Table Question Answering on FTQ
44.1AccuracyTabLaP-EW
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TabLaP-EWLearning Paradigm=Proposed (Ours)2024.10 | 44.1 | 53.8 | |
| TabLaPLearning Paradigm=Proposed (Ours)2024.10 | 44.1 | 53.7 | |
| GPT-4oLearning Paradigm=Zero-shot LLM2024.10 | 41.7 | — | |
| Mix-SCLearning Paradigm=Zero-shot LLM2024.10 | 41.6 | — | |
| GPT-3.5 TurboLearning Paradigm=Zero-shot LLM2024.10 | 38.1 | — | |
| OmniTab-LargeLearning Paradigm=Fine-tuned PLM2024.10 | 25.2 | — | |
| TAPEX-LargeLearning Paradigm=Fine-tuned PLM2024.10 | 19.8 | — |