List your company

Report Generation on MIMIC (Factual Consistency and Completeness)

54.9Factual Consistency (FC)clean RAG
5.312818.186431.0643.9336May 11, 2026

Evaluation results

MethodLinks
clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.0554.956.86
LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.0551.6653.22
M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.0548.9650.25
clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.0541.1843.14
LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0539.6141.85
M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.0538.1240.63
w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.0533.3334.44
clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.0531.3741.18
LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0529.9638.77
clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.0529.4139.22
M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.0528.7636.78
LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0526.4635.49
M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.0524.3132.7
clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.0519.6115.69
w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.0518.8919.44
LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0518.3614.81
M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.0517.3814.08
w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.0517.2220.56
w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.0512.2212.78
w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.057.224.45