Uncertainty Estimation on Movies (test)
66.56AUPRC (pp)Signatures
Evaluation Results
| Method | Links | |
|---|---|---|
| SignaturesTrain=Movies, Backbone=Mistral-7B-Instruct-v0.32026.03 | 66.56 | |
| SignaturesTrain=HotpotQA, Backbone=Mistral-7B-Instruct-v0.32026.03 | 61.38 | |
| LOS-NETTrain=HotpotQA, Backbone=Mistral-7B-Instruct-v0.32026.03 | 58.98 | |
| LOS-NETTrain=Movies, Backbone=Mistral-7B-Instruct-v0.32026.03 | 58.98 | |
| LOS-NETTrain=IMDB, Backbone=Mistral-7B-Instruct-v0.32026.03 | 58.98 | |
| SignaturesTrain=IMDB, Backbone=Mistral-7B-Instruct-v0.32026.03 | 51.72 |