Natural Language Inference on ContractNLI
84.5Macro-F1Full DRO
Evaluation Results
| Method | Links | |
|---|---|---|
| Full DROReward=DRO, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=true2025.06 | 84.5 | |
| R3Reward=R3, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=false2025.06 | 80.8 | |
| R3Reward=R3, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.06 | 80.6 | |
| Avg Prob (RLPR)Reward=Avg Prob (RLPR), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.06 | 78.2 | |
| Rubric (RLER)Reward=Rubric (RLER), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.06 | 75.4 | |
| Avg Logprob (VeriFree)Reward=Avg Logprob (VeriFree), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.06 | 73.6 | |
| RL-F1Reward=RL-F1, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.06 | 73.4 | |
| BaseReward=Base2025.06 | 68.1 |