List your company

Multi-hop Reasoning on HotpotQA IRCoT (500 samples) (test)

54.6ACCActiShade
17.99227.4963746.504Jan 12, 2026

Evaluation results

MethodLinks
ActiShadeBackbone=Llama-3-8B-Instruct, Retrieval Mode=Active/Iterative retrieval2026.0154.656.33
ActiShadeBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Active/Iterative retrieval2026.0153.9757.45
DRAGINBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Multi-round retrieval2026.0151.2154.3
DRAGINBackbone=Llama-3-8B-Instruct, Retrieval Mode=Multi-round retrieval2026.0150.8752.52
Iter-RetGenBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Multi-round retrieval2026.0149.0351.04
FLAREBackbone=Llama-3-8B-Instruct, Retrieval Mode=Multi-round retrieval2026.0148.4550.4
Iter-RetGenBackbone=Llama-3-8B-Instruct, Retrieval Mode=Multi-round retrieval2026.0148.2349.41
ActiShadeBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Active/Iterative retrieval2026.0148.255.45
IRCoTBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Multi-round retrieval2026.0147.9850.5
SelfASKBackbone=Llama-3-8B-Instruct, Retrieval Mode=Multi-round retrieval2026.0147.148.7
Direct-RBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Single-round retrieval2026.0146.248.11
DRAGINBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Multi-round retrieval2026.0146.150.3
SelfASKBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Multi-round retrieval2026.0145.9747.19
Iter-RetGenBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Multi-round retrieval2026.0144.448.24
IRCoTBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Multi-round retrieval2026.0143.7948.13
Direct-RBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Single-round retrieval2026.014347.99
SelfASKBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Multi-round retrieval2026.0142.1846.1
FLAREBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=Multi-round retrieval2026.0142.1444.87
FLAREBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=Multi-round retrieval2026.0140.1942.03
IRCoTBackbone=Llama-3-8B-Instruct, Retrieval Mode=Multi-round retrieval2026.0140.147.03
Direct-RBackbone=Llama-3-8B-Instruct, Retrieval Mode=Single-round retrieval2026.0137.744.89
CoTBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=None2026.0129.434.92
CoTBackbone=Llama-3-8B-Instruct, Retrieval Mode=None2026.012934.09
DirectBackbone=Qwen2.5-14B-Instruct, Retrieval Mode=None2026.0127.232.94
DirectBackbone=Llama-3-8B-Instruct, Retrieval Mode=None2026.0122.425.34
CoTBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=None2026.012227.61
DirectBackbone=Qwen2.5-7B-Instruct, Retrieval Mode=None2026.0119.419.52