List your company

Multiple-Choice Question Answering on IU-XRay

97.16Task Utilityclean RAG
-3.886422.346848.5874.8132May 11, 2026

Evaluation results

MethodLinks
clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.0597.16
LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.0595.68
M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.0593
clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.0588.65
LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0587.99
w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.0587.41
M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0586.33
w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.0584.44
clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.0568.8
LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0566.44
w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.0565.92
M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0563.35
clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.0557.45
LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0557.25
M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0556.19
w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.0549.63
clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.0517.73
LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0516.01
M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0514.2
w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.050