Image Classification on MHIST (Task Utility %)
78.03Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 78.03 | |
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 74.36 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 71.34 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 70.7 | |
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 67.03 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 65.63 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 63.06 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 60.46 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 60.21 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 55.49 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 55.4 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 52.97 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 37.14 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 31.43 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 12.14 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 12.14 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 12.14 | |
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 0 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 0 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 0 |