Document Visual Question Answering on VisualMRC (test)
55.76ROUGE-LLayoutLLM-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| LayoutLLM-7BModel Category=Ours, Evaluation Protocol=Zero-shot, Backbone Initialization=Vicuna-1.5-7B2024.04 | 55.76 | |
| LayoutLLM-7BModel Category=Ours, Evaluation Protocol=Zero-shot, Backbone Initialization=Llama2-7B-chat2024.04 | 55.73 | |
| Vicuna-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.04 | 53.63 | |
| Llama2-7B-chatModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.04 | 52.84 | |
| Vicuna-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.04 | 52.55 | |
| Vicuna-1.5-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.04 | 52.13 | |
| Llama2-7B-chatModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.04 | 49.26 | |
| Vicuna-1.5-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.04 | 47.22 | |
| Qwen-VL-7BModel Category=MLLM, Evaluation Protocol=Fine-tuned, Implementation=Original Paper2024.04 | 42.52 | |
| LLaVAR-7BModel Category=MLLM, Evaluation Protocol=Zero-shot, Implementation=Original Paper2024.04 | 36.37 | |
| LLaVA-1.5-7BModel Category=MLLM, Evaluation Protocol=Zero-shot2024.04 | 35.23 | |
| Llama2-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.04 | 33.82 | |
| Llama2-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.04 | 29.73 |