| question-answering-on-fever | CoA | #1 | EM: 68.9 |
| question-answering-on-fever | Self-Ask | #3 | EM: 64.2 |
| question-answering-on-fever | DSP | #5 | EM: 62.2 |
| question-answering-on-fever | CoA w/o actions | #6 | EM: 54.2 |
| question-answering-on-fever | Zero-shot | #8 | EM: 50 |
| question-answering-on-strategyqa | CoA | #3 | EM: 79.2 |
| question-answering-on-strategyqa | SearchChain | #5 | EM: 77 |
| question-answering-on-strategyqa | CoA w/o actions | #6 | EM: 70.6 |
| question-answering-on-strategyqa | Least-to-Most | #8 | EM: 65.8 |
| question-answering-on-truthfulqa | CoA | #26 | EM: 67.3 |
| question-answering-on-truthfulqa | CoA w/o actions | #28 | EM: 63.3 |
| question-answering-on-webquestions | CoA | #1 | EM: 70.7 |
| question-answering-on-webquestions | CoA w/o actions | #2 | EM: 64.7 |
| question-answering-on-webquestions | DSP | #4 | EM: 59.4 |
| question-answering-on-webquestions | Few-shot | #7 | EM: 44.7 |
| question-answering-on-webquestions | Zero-shot | #10 | EM: 43 |
| question-answering-on-webquestions | CoT | #13 | EM: 42.5 |
| question-answering-on-webquestions | React | #18 | EM: 38.3 |
| question-answering-on-webquestions | Self-Ask | #21 | EM: 31.1 |
| question-answering-on-webquestions | ToT | #25 | EM: 26.3 |