Multiple-Choice Question Answering on IU-XRay
97.16Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 97.16 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 95.68 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 93 | |
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 88.65 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 87.99 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 87.41 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 86.33 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 84.44 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 68.8 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 66.44 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 65.92 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 63.35 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 57.45 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 57.25 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 56.19 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 49.63 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 17.73 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 16.01 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 14.2 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 0 |