True/False Question Answering on MIMIC
77.78Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 77.78 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 75.18 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 71.7 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 68.88 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 66 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 63.78 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 61.34 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 58.9 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 51.12 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 47.96 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 46.66 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 44.6 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 40.66 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 35.12 | |
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 31.7 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 30.42 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 27.82 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 24 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 22.66 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 0 |