True/False Question Answering on IU-XRay
95.92Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 95.92 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 93.4 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 92.5 | |
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 91.84 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 90.96 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 89.06 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 88.28 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 79.6 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 79.38 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 77 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 68.2 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 67.36 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 55.1 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 52.26 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 48.84 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 48.2 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 47.22 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 44.7 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 14.64 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 0 |