Hallucination Evaluation on Style-CHAIR
19.4Average CI ScoreFuyu
Evaluation results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FuyuPrompt=Provide a one-sentence caption for the provided image.2025.08 | 19.4 | 20.6 | 69.3 | 19.1 | 69.7 | 25 | 59.3 | 16.9 | 58.7 | 19.7 | 53.7 | 14.9 | 59.3 | 61.7 | |
| GreedyModel=MiniGPT-42025.08 | 10.6 | — | — | — | — | — | — | — | — | — | — | — | — | 33.9 | |
| GreedyModel=LLaVA-1.52025.08 | 10.3 | — | — | — | — | — | — | — | — | — | — | — | — | 35.3 | |
| GreedyModel=InstructBLIP2025.08 | 10.1 | — | — | — | — | — | — | — | — | — | — | — | — | 35.2 | |
| SAVERModel=LLaVA-1.52025.08 | 9.7 | — | — | — | — | — | — | — | — | — | — | — | — | 30 | |
| GreedyModel=LLaVA-1.62025.08 | 9.4 | — | — | — | — | — | — | — | — | — | — | — | — | 23.9 | |
| MiniGPT-4-7bPrompt=Provide a one-sentence caption for the provided image.2025.08 | 9.1 | 11.4 | 27 | 9.1 | 20.3 | 10.5 | 21 | 9 | 21.7 | 9.4 | 23.3 | 5.4 | 14 | 21.2 | |
| SAVERModel=LLaVA-1.62025.08 | 8.8 | — | — | — | — | — | — | — | — | — | — | — | — | 20 | |
| SAVERModel=MiniGPT-42025.08 | 8.3 | — | — | — | — | — | — | — | — | — | — | — | — | 27.3 | |
| SAVERModel=InstructBLIP2025.08 | 8.1 | — | — | — | — | — | — | — | — | — | — | — | — | 27.3 | |
| Qwen-VLPrompt=Provide a one-sentence caption for the provided image.2025.08 | 7 | 8.4 | 15 | 6.4 | 13 | 9.5 | 14.7 | 7.1 | 12 | 7.4 | 14.3 | 3.1 | 6.3 | 12.6 | |
| LLaVA-1.5Prompt=Provide a one-sentence caption for the provided image.2025.08 | 6.9 | 9.1 | 19.3 | 7.2 | 14 | 8.2 | 16 | 6.9 | 13 | 7.1 | 13.7 | 2.6 | 5.7 | 13.6 | |
| LLaVA-1.5-13bPrompt=Provide a one-sentence caption for the provided image.2025.08 | 6.6 | 8.1 | 16.7 | 5.4 | 10.3 | 8.9 | 17.3 | 6.6 | 13.3 | 6.2 | 12.3 | 4.3 | 8.7 | 13.1 | |
| Phi3VPrompt=Provide a one-sentence caption for the provided image.2025.08 | 6.3 | 7.9 | 14 | 5.9 | 11 | 8 | 13.7 | 6.8 | 11.7 | 6.3 | 12 | 3.1 | 5.3 | 11.3 | |
| Idefics2-8bPrompt=Provide a one-sentence caption for the provided image.2025.08 | 6.3 | 9.7 | 14 | 6.8 | 9.7 | 6.6 | 9.7 | 5.8 | 9.7 | 6 | 9 | 2.7 | 5 | 9.5 | |
| TinyllavaPrompt=Provide a one-sentence caption for the provided image.2025.08 | 5.3 | 6.1 | 12.3 | 5.6 | 11.7 | 5.8 | 12.3 | 5.2 | 11.3 | 6.6 | 14 | 2.5 | 5.3 | 11.2 | |
| mPLUG-Owl2Prompt=Provide a one-sentence caption for the provided image.2025.08 | 4.7 | 5.6 | 8.3 | 5.6 | 8.3 | 6.2 | 8 | 4.7 | 6 | 4.3 | 6.3 | 1.6 | 2.7 | 6.6 | |
| InstructBILPPrompt=Provide a one-sentence caption for the provided image.2025.08 | 4.2 | 5.8 | 10.3 | 5 | 9 | 5.2 | 8.3 | 3 | 5 | 4.3 | 6.7 | 2 | 4 | 7.2 | |
| LLaVA-v1.6-mistral-7bPrompt=Provide a one-sentence caption for the provided image.2025.08 | 4 | 6.5 | 8.7 | 3.2 | 4.3 | 4.1 | 5.3 | 4.8 | 6.7 | 4.4 | 6 | 1.2 | 1.7 | 5.5 | |
| Gemini-1.5-PROPrompt=Provide a one-sentence caption for the provided image.2025.08 | 3.8 | 4.9 | 6 | 3 | 4.3 | 2.3 | 2.7 | 6.9 | 9 | 3.4 | 4.7 | 2.3 | 3.7 | 5.1 | |
| GPT4oPrompt=Provide a one-sentence caption for the provided image.2025.08 | 3.4 | 6.2 | 7 | 3.1 | 3.7 | 2.4 | 2.7 | 4.3 | 6 | 3.6 | 5 | 0.7 | 0.5 | 4.2 |