Structural Reasoning on CREAK
86.5AccuracyAlways Tell Me The Odds
Evaluation Results
| Method | Links | |
|---|---|---|
| Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct, Data Augmentation=+Syn, Training Strategy=+R, Reasoning Framework=Maieutic Prompting2025.05 | 86.5 | |
| Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct, Data Augmentation=+Syn, Reasoning Framework=Maieutic Prompting2025.05 | 85.6 | |
| Always Tell Me The OddsBackbone=Qwen2.5-14B-Instruct, Reasoning Framework=Maieutic Prompting2025.05 | 84.8 | |
| Always Tell Me The OddsBackbone=Qwen2.5-8B-Instruct, Reasoning Framework=Maieutic Prompting2025.05 | 83.2 | |
| Always Tell Me The OddsBackbone=Qwen2.5-7B-Instruct, Reasoning Framework=Maieutic Prompting2025.05 | 82.8 | |
| GPT-4oEvaluation Protocol=0-Shot, Reasoning Framework=Maieutic Prompting2025.05 | 81.1 | |
| DeepSeek-R1-Distill-Qwen-32BEvaluation Protocol=0-Shot, Reasoning Framework=Maieutic Prompting2025.05 | 68 | |
| RoBERTa-LType=Encoder, Reasoning Framework=Maieutic Prompting2025.05 | 62.5 | |
| Llama-3-InstructEvaluation Protocol=Probe, Size=14B, Reasoning Framework=Maieutic Prompting2025.05 | 42.1 |