Binary Classification on IBD Cohort Clinical label ground truth
80Accuracy (Random Ordering)RAG-LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RAG-LLMBudget (t)=2162026.06 | 80 | — | — | |
| waldBudget (t)=502026.06 | 73 | -6.8 | -7.1 | |
| waldBudget (t)=1002026.06 | 71 | -4.9 | -5 | |
| waldBudget (t)=102026.06 | 70 | -0.5 | -0.5 | |
| MRF-LLMBudget (t)=2162026.06 | 70 | — | — | |
| waldBudget (t)=1502026.06 | 69 | -3.2 | -3.8 | |
| waldBudget (t)=2162026.06 | 65 | — | — | |
| two_elboBudget (t)=2162026.06 | 65 | — | — | |
| stack-ABudget (t)=2162026.06 | 65 | — | — | |
| two_elboBudget (t)=1502026.06 | 64 | 0 | 0.5 | |
| stack-ABudget (t)=1502026.06 | 60 | 3 | 2.3 | |
| two_elboBudget (t)=1002026.06 | 58 | 4.6 | 4.3 | |
| two_elboBudget (t)=502026.06 | 53 | 6.1 | 5.2 | |
| stack-ABudget (t)=1002026.06 | 53 | 8.3 | 8.1 | |
| two_elboBudget (t)=102026.06 | 50 | 4.1 | 4.6 | |
| stack-ABudget (t)=502026.06 | 48 | 8.9 | 7.1 | |
| stack-ABudget (t)=102026.06 | 46 | 3.4 | 3.9 | |
| RAG-LLMBudget (t)=1002026.06 | 46 | — | — | |
| RAG-LLMBudget (t)=1502026.06 | 44 | — | — | |
| RAG-LLMBudget (t)=502026.06 | 42 | — | — | |
| MRF-LLMBudget (t)=1002026.06 | 38 | — | — | |
| RAG-LLMBudget (t)=102026.06 | 34 | — | — | |
| MRF-LLMBudget (t)=502026.06 | 34 | — | — | |
| MRF-LLMBudget (t)=1502026.06 | 28 | — | — | |
| MRF-LLMBudget (t)=102026.06 | 24 | — | — |