Word Reasoning on Acronym (4,5) (OOD)
12.3AccuracyBOLT -> GRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| BOLT -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.12 | 12.3 | |
| SkillFactory -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.12 | 12.1 | |
| STaR -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.12 | 9.8 | |
| R1 Distillbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.12 | 9.4 | |
| RL-Onlybase_model=Qwen2.5-1.5B-Instruct, training=RL2025.12 | 8.7 | |
| Qwen2.5 1.5B Instructbase_model=Qwen2.5-1.5B-Instruct, training=None2025.12 | 6.9 | |
| BOLTbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.12 | 6.2 | |
| R1 Distill -> GRPObase_model=Qwen2.5-1.5B-Instruct, training=SFT + GRPO2025.12 | 6 | |
| STaRbase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.12 | 4 | |
| SkillFactorybase_model=Qwen2.5-1.5B-Instruct, training=SFT2025.12 | 3 |