List your company

Multiple-Choice Question Answering on MIMIC

80.96Task Utilityclean RAG
5.747225.273644.864.3264May 11, 2026

Evaluation results

MethodLinks
clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.0580.96
LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.0576.57
w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.0574.69
M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.0572.96
clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.0571.43
LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0567.09
M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0563.36
clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.0561.9
w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.0559.26
LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0558.09
w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.0558.02
clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.0555.56
M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0554.97
LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0551.38
M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0547.99
w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.0533.96
LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0511.32
M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0511.24
clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.0511.11
w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.058.64