Performance Prediction on AmericasNLP Spanish to Bribri 2023 (test)
0.32MAELLM-PP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLM-PPBackbone=GPT-42023.10 | 0.32 | 0.2 | |
| Neuron-wise MoSPredictor Type=Supernet-based2023.10 | 0.43 | 0.09 | |
| Layer-wise MoSPredictor Type=Supernet-based2023.10 | 0.63 | -0.14 | |
| HATPredictor Type=Supernet-based2023.10 | 0.72 | 0.02 |