List your company

Intrinsic Reasoning on UNLI

0.813Spearman CorrelationAlways Tell Me The Odds
0.621640.671320.7210.77068May 2, 2025

Evaluation results

MethodLinks
Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct2025.050.813
Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct, Data Augmentation=+Syn2025.050.812
Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct, Data Augmentation=+Syn, Training Strategy=+R2025.050.812
Always Tell Me The OddsBackbone=Qwen2.5-8B-Instruct2025.050.804
Always Tell Me The OddsBackbone=Qwen2.5-7B-Instruct2025.050.802
RoBERTa-LType=Encoder2025.050.707
GPT-4oEvaluation Protocol=0-Shot2025.050.699
Llama-3-InstructEvaluation Protocol=Probe, Size=14B2025.050.681
DeepSeek-R1-Distill-Qwen-32BEvaluation Protocol=0-Shot2025.050.629