Question Answering on TriviaQA (Corr., Err.)
2,727CorrelationBalanceRAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.05 | 2,727 | 13.96 | |
| BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.05 | 2,691 | 13.16 | |
| LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.05 | 2,652 | 14.13 | |
| BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.05 | 2,584 | 12.06 | |
| LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.05 | 2,529 | 13.14 | |
| UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.05 | 2,434 | 13.67 | |
| BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.05 | 2,430 | 10.84 | |
| LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.05 | 2,382 | 12.14 | |
| UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.05 | 2,360 | 12.72 | |
| BalanceRAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.05 | 2,288 | 9.91 | |
| UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.05 | 2,264 | 11.78 | |
| LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.152026.05 | 2,218 | 14.15 | |
| LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.05 | 2,198 | 11.1 | |
| LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.142026.05 | 2,165 | 13.18 | |
| UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.05 | 2,084 | 10.72 | |
| BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.05 | 2,073 | 13.84 | |
| LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.132026.05 | 2,070 | 12.15 | |
| LLM-RAGBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.05 | 2,036 | 10.06 | |
| BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.05 | 1,973 | 12.87 | |
| LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.122026.05 | 1,928 | 11.08 | |
| UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.05 | 1,917 | 13.2 | |
| LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.05 | 1,876 | 14.07 | |
| BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.05 | 1,873 | 12.01 | |
| UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.05 | 1,850 | 12.14 | |
| UCB-CascadedBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.05 | 1,849 | 9.78 | |
| LLM-onlyBackbone=Llama3.1-8B, Target risk level (alpha)=0.112026.05 | 1,780 | 10.04 | |
| BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.05 | 1,774 | 10.91 | |
| LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.05 | 1,760 | 13.02 | |
| UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.05 | 1,749 | 11.13 | |
| LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.05 | 1,646 | 11.92 | |
| BalanceRAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.05 | 1,643 | 9.9 | |
| LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.05 | 1,532 | 10.75 | |
| UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.05 | 1,488 | 10.37 | |
| LLM-RAGBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.05 | 1,390 | 9.49 | |
| LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.152026.05 | 1,371 | 13.73 | |
| LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.142026.05 | 1,283 | 12.74 | |
| LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.132026.05 | 1,214 | 11.75 | |
| LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.122026.05 | 1,116 | 10.7 | |
| UCB-CascadedBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.05 | 1,028 | 9.41 | |
| LLM-onlyBackbone=Llama3.2-3B, Target risk level (alpha)=0.112026.05 | 988 | 9.55 |