List your company

Multi-hop Question Answering on 2WikiMultiHopQA (official evaluation)

31.8Exact Match (EM)HRPO
10.27215.86121.4527.039Dec 1, 2025

Evaluation results

MethodLinks
HRPOBackbone=Qwen2.5-3B-Instruct, Strategy=Hybrid Reasoning Policy Optimization, Context Retrieval=Top-3 documents2025.1231.8
M3POBackbone=Qwen2.5-3B-Instruct, Strategy=Multi-Path Perception Policy Optimization, Context Retrieval=Top-3 documents2025.1231.4
GRPOBackbone=Qwen2.5-3B-Instruct, Strategy=GRPO, Context Retrieval=Top-3 documents2025.1230.3
PPOBackbone=Qwen2.5-3B-Instruct, Strategy=PPO, Context Retrieval=Top-3 documents2025.1229.3
M3POBackbone=Qwen2.5-1.5B-Instruct, Strategy=Multi-Path Perception Policy Optimization, Context Retrieval=Top-3 documents2025.1227.9
HRPOBackbone=Qwen2.5-1.5B-Instruct, Strategy=Hybrid Reasoning Policy Optimization, Context Retrieval=Top-3 documents2025.1227.6
QABackbone=Qwen2.5-7B-Instruct, Strategy=Direct inference, Context Retrieval=Top-3 documents2025.1225
SFTBackbone=Qwen2.5-3B-Instruct, Strategy=Supervised Fine-Tuning, Context Retrieval=Top-3 documents2025.1224.8
PPOBackbone=Qwen2.5-1.5B-Instruct, Strategy=PPO, Context Retrieval=Top-3 documents2025.1224.2
RAGBackbone=Qwen2.5-7B-Instruct, Strategy=Retrieval-Augmented Generation, Context Retrieval=Top-3 documents2025.1223.5
RAGBackbone=Qwen2.5-3B-Instruct, Strategy=Retrieval-Augmented Generation, Context Retrieval=Top-3 documents2025.1222.6
GRPOBackbone=Qwen2.5-1.5B-Instruct, Strategy=GRPO, Context Retrieval=Top-3 documents2025.1221.3
SFTBackbone=Qwen2.5-1.5B-Instruct, Strategy=Supervised Fine-Tuning, Context Retrieval=Top-3 documents2025.1221
RAGBackbone=Qwen2.5-1.5B-Instruct, Strategy=Retrieval-Augmented Generation, Context Retrieval=Top-3 documents2025.1220.3
Search-o1Backbone=Qwen2.5-7B-Instruct, Strategy=Search-o1, Context Retrieval=Top-3 documents2025.1217.6
IRCoTBackbone=Qwen2.5-7B-Instruct, Strategy=Interleaved retrieval with CoT, Context Retrieval=Top-3 documents2025.1214.9
CoTBackbone=Qwen2.5-7B-Instruct, Strategy=Chain-of-Thought, Context Retrieval=Top-3 documents2025.1211.1