List your company

Question Answering on TriviaQA (Corr., Err.)

2,727CorrelationBalanceRAG
918.441,387.971,857.52,327.03May 19, 2026

Evaluation results

MethodLinks
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.052,72713.96
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.052,69113.16
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.052,65214.13
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.052,58412.06
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.052,52913.14
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.052,43413.67
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.052,43010.84
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.052,38212.14
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.052,36012.72
BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.052,2889.91
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.052,26411.78
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.052,21814.15
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.052,19811.1
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.052,16513.18
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.052,08410.72
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.052,07313.84
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.052,07012.15
LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.052,03610.06
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.051,97312.87
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.051,92811.08
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.051,91713.2
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.051,87614.07
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.051,87312.01
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.051,85012.14
UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.051,8499.78
LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.051,78010.04
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.051,77410.91
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.051,76013.02
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.051,74911.13
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.051,64611.92
BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.051,6439.9
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.051,53210.75
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.051,48810.37
LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.051,3909.49
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.051,37113.73
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.051,28312.74
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.051,21411.75
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.051,11610.7
UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.051,0289.41
LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.059889.55