List your company

Question Answering on 2WikiQA (test)

57.9EMSearch-R1
14.42825.7143748.286Feb 11, 2026Mar 2, 2026Mar 21, 2026Apr 10, 2026Apr 29, 2026May 18, 2026Jun 7, 2026

Evaluation results

MethodLinks
Search-R1LLM Generator=Qwen2.5-7B-Instruct2026.0257.964.9
MultiCube-RAGLLM Generator=Qwen2.5-7B-Instruct2026.0256.363.2
s3LLM Generator=Qwen2.5-7B-Instruct2026.0247.755.2
TrustMarginBackbone=LLaMA3.1-8B2026.0632.739.48
BM25-RAGBackbone=LLaMA3.1-8B2026.0627.334.3
DTR-RAGBackbone=LLaMA3.1-8B2026.0627.333.67
IRCoTBackbone=LLaMA3.1-8B2026.0626.233.12
DirectBackbone=LLaMA3.1-8B2026.0624.930.98
FLAREBackbone=LLaMA3.1-8B2026.0624.931.61
TrustMarginBackbone=LLaMA3.2-3B2026.0622.930.29
CLeHe-RAGBackbone=LLaMA3.1-8B2026.0622.927.13
DTR-RAGBackbone=LLaMA3.2-3B2026.0621.527.65
IRCoTBackbone=LLaMA3.2-3B2026.0620.727.45
CLeHe-RAGBackbone=LLaMA3.2-1B2026.0620.426.14
DTR-RAGBackbone=LLaMA3.2-1B2026.0620.426.26
TrustMarginBackbone=LLaMA3.2-1B2026.0620.427.29
IRCoTBackbone=LLaMA3.2-1B2026.0620.126.32
BM25-RAGBackbone=LLaMA3.2-1B2026.0619.426.4
BM25-RAGBackbone=LLaMA3.2-3B2026.0618.825.33
DirectBackbone=LLaMA3.2-3B2026.0617.924.27
FLAREBackbone=LLaMA3.2-3B2026.0617.924.04
FLAREBackbone=LLaMA3.2-1B2026.0616.622.77
CLeHe-RAGBackbone=LLaMA3.2-3B2026.0616.323.13
DirectBackbone=LLaMA3.2-1B2026.0616.122.17