List your company

Question Answering on NQ (Corr. and Err.)

763Correlation ScoreLLM-RAG
93.24267.12441614.88May 19, 2026

Evaluation results

MethodLinks
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.182026.0576314.78
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.192026.0576314.78
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.172026.0576014.66
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.192026.0575915.17
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.182026.0575715.23
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.172026.0575315.11
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.162026.0575214.22
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.192026.0574715.81
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.182026.0574314.92
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.162026.0574114.2
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.172026.0573614.08
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.0573413.31
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.162026.0571813.07
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.0570913.15
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.0569812.14
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.192026.0561516.97
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.192026.0561516.62
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.182026.0559016.01
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.192026.0559015.82
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.182026.0557515.06
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.182026.0556315.2
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.172026.0556214.97
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.162026.0553213.9
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.172026.0553114.04
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.162026.0549213.12
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.0548912.83
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.0544712.2
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.192026.0532016.3
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.182026.0528314.93
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.172026.0524013.62
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.162026.0519111.84
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.0515810.55
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.192026.0513415.72
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.182026.0512515.52
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.172026.0511915.68