Visual Question Answering on E-VQA
53.7AccuracyQKVQA
Evaluation results
| Method | Links | |
|---|---|---|
| QKVQAGenerator=LLaMA-3-8B, Gen. FT=false, Filter. FT=true2026.01 | 53.7 | |
| QKVQAGenerator=Qwen2.5-VL-7B, Gen. FT=false, Filter. FT=true2026.01 | 53.7 | |
| OMGMGenerator=LLaMA-3-8B, Gen. FT=false, Filter. FT=true, Note=Reproduction2026.01 | 49.7 | |
| QKVQAGenerator=LLaMA-3.1-8B, Gen. FT=true, Filter. FT=true, Support=ReflectiVA2026.01 | 49.5 | |
| OMGMGenerator=Qwen2.5-VL-7B, Gen. FT=false, Filter. FT=true, Note=Reproduction2026.01 | 48.8 | |
| OMGMGenerator=LLaMA-3.1-8B, Gen. FT=true, Filter. FT=true, Support=ReflectiVA2026.01 | 46.5 | |
| EchoSightGenerator=LLaMA-3-8B, Gen. FT=false, Filter. FT=true2026.01 | 41.8 | |
| mKG-RAGGenerator=LLaMA-3.1-8B, Gen. FT=true, Filter. FT=true2026.01 | 38.4 | |
| VLM-PRFGenerator=LLaMA-3.1-8B, Gen. FT=true, Filter. FT=true2026.01 | 36.3 | |
| ReflectiVAGenerator=LLaMA-3.1-8B, Gen. FT=true, Filter. FT=true2026.01 | 35.5 | |
| GPT-4VGenerator=GPT-4V, Gen. FT=false, Filter. FT=false2026.01 | 26.9 | |
| Qwen2.5-VL-7BGenerator=Qwen2.5-VL-7B, Gen. FT=false, Filter. FT=false2026.01 | 23.6 | |
| GPT-4Generator=GPT-4, Gen. FT=false, Filter. FT=false2026.01 | 21.9 | |
| LLaMA-3.1-8BGenerator=LLaMA-3.1-8B, Gen. FT=false, Filter. FT=false2026.01 | 16.5 | |
| LLaMA-3-8BGenerator=LLaMA-3-8B, Gen. FT=false, Filter. FT=false2026.01 | 16.3 |