List your company
ResearchFormerly WizWand

Knowledge-Intensive Reasoning on 2wikiMultiHopQA (F1 Score)

76.1F1 ScoreQwen2.5-7B + GRPO
6.73224.74142.7560.759Dec 11, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, Algorithm=GRPO2025.1276.1
Qwen2.5-7B + ARPOBase Model=Qwen2.5-7B, Algorithm=ARPO2025.1276.1
Llama3.1-8B + ARPOBase Model=Llama3.1-8B, Algorithm=ARPO2025.1275.5
Llama3.1-8B + GRPOBase Model=Llama3.1-8B, Algorithm=GRPO2025.1271.8
Llama3.1-8B + Reinforce ++Base Model=Llama3.1-8B, Algorithm=Reinforce ++2025.1271.6
Llama3.1-8B + DAPOBase Model=Llama3.1-8B, Algorithm=DAPO2025.1270.3
Qwen2.5-7B + Reinforce ++Base Model=Qwen2.5-7B, Algorithm=Reinforce ++2025.1268.9
Qwen2.5-7B + DAPOBase Model=Qwen2.5-7B, Algorithm=DAPO2025.1268.4
Qwen2.5-3B + ARPOBase Model=Qwen2.5-3B, Algorithm=ARPO2025.1267.4
Qwen2.5-3B + GRPOBase Model=Qwen2.5-3B, Algorithm=GRPO2025.1264.5
Qwen2.5-3B + DAPOBase Model=Qwen2.5-3B, Algorithm=DAPO2025.1262.5
Qwen2.5-3B + Reinforce ++Base Model=Qwen2.5-3B, Algorithm=Reinforce ++2025.1262.3
Llama3.1-8B + TIR PromptingBase Model=Llama3.1-8B, Algorithm=TIR Prompting2025.1247.5
Llama3.1-8BBase Model=Llama3.1-8B, Algorithm=Direct Reasoning2025.1224.6
Qwen2.5-7B + TIR PromptingBase Model=Qwen2.5-7B, Algorithm=TIR Prompting2025.1218.3
Qwen2.5-3B + TIR PromptingBase Model=Qwen2.5-3B, Algorithm=TIR Prompting2025.1214.1
Qwen2.5-7BBase Model=Qwen2.5-7B, Algorithm=Direct Reasoning2025.1212.6
Qwen2.5-3BBase Model=Qwen2.5-3B, Algorithm=Direct Reasoning2025.129.4