List your company

Natural Language Inference on ContractNLI

84.5Macro-F1Full DRO
67.44471.87276.380.728Jun 16, 2025

Evaluation results

MethodLinks
Full DROReward=DRO, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=true2025.0684.5
R3Reward=R3, Rollout-Group Rejection (Rubric)=true, Rollout-Group Rejection (Variance)=false2025.0680.8
R3Reward=R3, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0680.6
Avg Prob (RLPR)Reward=Avg Prob (RLPR), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0678.2
Rubric (RLER)Reward=Rubric (RLER), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0675.4
Avg Logprob (VeriFree)Reward=Avg Logprob (VeriFree), Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0673.6
RL-F1Reward=RL-F1, Rollout-Group Rejection (Rubric)=false, Rollout-Group Rejection (Variance)=false2025.0673.4
BaseReward=Base2025.0668.1