List your company

Abstention on HotpotQA

76.8Abstain AccuracyR2C
62.2466.0269.873.58Oct 13, 2025

Evaluation results

MethodLinks
R2CRAG Framework=ReAct, Confidence Threshold=0.92025.1076.885.08
SelfCRAG Framework=ReAct, Confidence Threshold=0.92025.1075.883.8
ReaCRAG Framework=ReAct, Confidence Threshold=0.92025.1075.483.17
R2CRAG Framework=ReSearch, Confidence Threshold=0.92025.1074.878.71
R2CRAG Framework=SelfAsk, Confidence Threshold=0.92025.1074.481.76
R2CRAG Framework=Search-o1, Confidence Threshold=0.92025.1074.482.22
R2CRAG Framework=Search-R1, Confidence Threshold=0.92025.1073.477.57
RrrCRAG Framework=ReAct, Confidence Threshold=0.92025.1072.280.82
ReaCRAG Framework=Search-o1, Confidence Threshold=0.92025.1071.479.48
P(true)RAG Framework=ReSearch, Confidence Threshold=0.92025.1071.473.46
P(true)RAG Framework=SelfAsk, Confidence Threshold=0.92025.1070.875.33
P(true)RAG Framework=Search-R1, Confidence Threshold=0.92025.107071.15
SelfCRAG Framework=Search-o1, Confidence Threshold=0.92025.106978.07
ReaCRAG Framework=Search-R1, Confidence Threshold=0.92025.1068.871.11
SelfCRAG Framework=ReSearch, Confidence Threshold=0.92025.1068.675.19
ReaCRAG Framework=ReSearch, Confidence Threshold=0.92025.1068.672.6
P(true)RAG Framework=ReAct, Confidence Threshold=0.92025.1067.273.46
RrrCRAG Framework=Search-o1, Confidence Threshold=0.92025.1066.271.5
P(true)RAG Framework=Search-o1, Confidence Threshold=0.92025.1065.871.73
RrrCRAG Framework=SelfAsk, Confidence Threshold=0.92025.1065.670.54
ReaCRAG Framework=SelfAsk, Confidence Threshold=0.92025.1064.670.45
RrrCRAG Framework=ReSearch, Confidence Threshold=0.92025.1064.463.37
SelfCRAG Framework=SelfAsk, Confidence Threshold=0.92025.1064.269.51
RrrCRAG Framework=Search-R1, Confidence Threshold=0.92025.106461.2
SelfCRAG Framework=Search-R1, Confidence Threshold=0.92025.1062.862.34