Counterfactual Reasoning on CRAFT Easy Split (test)
80.05AccuracyBERT-D
Evaluation results
| Method | Links | |
|---|---|---|
| BERT-DLearning Protocol=Supervised (34K instances)2025.06 | 80.05 | |
| CRCG_GPT4Learning Protocol=Few-shot, Proxy Simulator=GPT-42025.06 | 79.68 | |
| GPT-4 with CRCG guided promptLearning Protocol=Few-shot, Prompt Engineering=Causal graph guided2025.06 | 78.07 | |
| GPT-4Learning Protocol=Few-shot, Model Version=gpt-4-06132025.06 | 77.93 | |
| CRCG_GPT3.5Learning Protocol=Few-shot, Proxy Simulator=GPT-3.52025.06 | 65.32 | |
| GPT-3.5 with CRCG guided promptLearning Protocol=Few-shot, Prompt Engineering=Causal graph guided2025.06 | 63.26 | |
| LSTM-DLearning Protocol=Supervised (34K instances)2025.06 | 55.89 | |
| GPT-3.5Learning Protocol=Few-shot, Model Version=gpt-3.5-turbo-06132025.06 | 52.29 |