Confidence Estimation (Freeform Tagging) on Bios
9.2Brier Score (BS)LOVEC-DPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LOVEC-DPOTagging Format=Freeform, Backbone=Llama3-8B-Instruct, Decoding Strategy=Greedy2025.05 | 9.2 | 6.1 | 67.4 | |
| LOVEC-GRPOTagging Format=Freeform, Backbone=Llama3-8B-Instruct, Decoding Strategy=Greedy2025.05 | 10.1 | 11.1 | 68.7 | |
| LOVEC-SFTTagging Format=Freeform, Backbone=Llama3-8B-Instruct, Decoding Strategy=Greedy2025.05 | 16.6 | 26.1 | 58.9 |