Multi-Hop QA on 2Wiki (Accuracy)
70.5AccuracySLEA-RL
Evaluation Results
| Method | Links | |
|---|---|---|
| SLEA-RLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 70.5 | |
| IGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 68.2 | |
| GSPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 60.1 | |
| PPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 59.7 | |
| GRPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 57.7 | |
| RLOOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 55 | |
| Reinforce++Base Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 54.5 | |
| GiGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 43.6 | |
| SkillRLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 43.2 | |
| EvolveRBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 38.2 | |
| Search-R1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 37 | |
| ZeroSearchBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 34.6 | |
| RAGBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 25.8 | |
| R1-InstructBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 20.8 | |
| Search-o1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 17 | |
| Qwen2.5Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 16.4 | |
| CoTBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 16.2 |