Image Classification on PCam (Task Utility %)
60.98Task Utilityclean RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| clean RAGModel=Gemini-2.5, Retriever=clean RAG, Top-K=12026.05 | 60.98 | |
| LIARModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 58.68 | |
| clean RAGModel=GPT-4o, Retriever=clean RAG, Top-K=12026.05 | 56.1 | |
| M3AttModel=Gemini-2.5, Retriever=SigLIP, Top-K=12026.05 | 54.88 | |
| LIARModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 52.74 | |
| clean RAGModel=Claude-4.5, Retriever=clean RAG, Top-K=12026.05 | 51.22 | |
| LIARModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 49.88 | |
| M3AttModel=GPT-4o, Retriever=SigLIP, Top-K=12026.05 | 47.44 | |
| M3AttModel=Claude-4.5, Retriever=SigLIP, Top-K=12026.05 | 47.38 | |
| w/o RAGModel=Gemini-2.5, Retriever=w/o RAG, Top-K=12026.05 | 43.44 | |
| clean RAGModel=GPT-5, Retriever=clean RAG, Top-K=12026.05 | 31.7 | |
| LIARModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 30.78 | |
| M3AttModel=GPT-5, Retriever=SigLIP, Top-K=12026.05 | 29.04 | |
| w/o RAGModel=Claude-4.5, Retriever=w/o RAG, Top-K=12026.05 | 21.22 | |
| w/o RAGModel=GPT-5, Retriever=w/o RAG, Top-K=12026.05 | 13.14 | |
| LIARModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 0.2 | |
| w/o RAGModel=GPT-4o, Retriever=w/o RAG, Top-K=12026.05 | 0 | |
| w/o RAGModel=LLaVA-Med, Retriever=w/o RAG, Top-K=12026.05 | 0 | |
| clean RAGModel=LLaVA-Med, Retriever=clean RAG, Top-K=12026.05 | 0 | |
| M3AttModel=LLaVA-Med, Retriever=SigLIP, Top-K=12026.05 | 0 |