Multiple-Choice Question Answering on MIMIC
80.96Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 80.96 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 76.57 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 74.69 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 72.96 | |
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 71.43 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 67.09 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 63.36 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 61.9 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 59.26 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 58.09 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 58.02 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 55.56 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 54.97 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 51.38 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 47.99 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 33.96 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 11.32 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 11.24 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 11.11 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 8.64 |