Multi-step reasoning on BamTwoogle (test)
74AccuracyReST meets ReAct
Evaluation Results
| Method | Links | |
|---|---|---|
| ReST meets ReActGeneration=2nd gen, Backbone=PaLM 2-L2023.12 | 74 | |
| PaLM 2-LMode=Pre-trained, Backbone=PaLM 2-L2023.12 | 68 | |
| ReST meets ReActGeneration=2nd gen, Backbone=PaLM 2-XS2023.12 | 63 | |
| ReST meets ReActGeneration=2nd gen, Backbone=PaLM 2-S2023.12 | 63 |