Natural Language Inference on ANLI (R1+R2+R3 Average)
59.6ANLI Avg Accuracyfs-X-ICL (ChatGPT)
Evaluation Results
| Method | Links | |
|---|---|---|
| fs-X-ICL (ChatGPT)Model=GPT3.5-turbo2023.11 | 59.6 | |
| ICLModel=Mistral 7B2023.11 | 39.8 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| fs-X-ICL (ChatGPT)Model=GPT3.5-turbo2023.11 | 59.6 | |
| ICLModel=Mistral 7B2023.11 | 39.8 |