Opinion Summarization on SUMMEVAL-OP 1.0 (Round-II)
5FL (Fluency)GPT-4
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GPT-4Model Category=LLMs2024.02 | 5 | 4.91 | 3.52 | 4.96 | 4.93 | 4.83 | 4.57 | |
| ChatGPT-3.5Model Category=LLMs2024.02 | 4.89 | 4.58 | 4.25 | 4.71 | 4.22 | 4.16 | 3.96 | |
| Solar-10.7BModel Category=LLMs2024.02 | 4.89 | 4.73 | 4.2 | 4.72 | 4.5 | 4.56 | 4.35 | |
| Zephyr-7BModel Category=LLMs2024.02 | 4.89 | 4.36 | 4.08 | 4.54 | 4.18 | 3.95 | 3.83 | |
| LLAMA2-13BModel Category=LLMs2024.02 | 4.87 | 4.49 | 4.25 | 4.62 | 4.02 | 4 | 3.94 | |
| Vicuna-13BModel Category=LLMs2024.02 | 4.87 | 4.41 | 4.09 | 4.43 | 4.03 | 4 | 3.77 | |
| Mistral-7BModel Category=LLMs2024.02 | 4.86 | 4.6 | 4.33 | 4.66 | 4.56 | 4.35 | 4.25 | |
| Vicuna-7BModel Category=LLMs2024.02 | 4.83 | 4.23 | 3.92 | 4.35 | 3.56 | 3.92 | 3.67 | |
| LLAMA2-7BModel Category=LLMs2024.02 | 4.79 | 4.34 | 3.77 | 4.49 | 3.67 | 3.79 | 3.46 | |
| LS-Sum-GModel Category=Pre-LLMs2024.02 | 4.76 | 4.4 | 2.87 | 2.74 | 2.32 | 3.03 | 2.69 | |
| MultimodalSumModel Category=Pre-LLMs2024.02 | 4.62 | 4.09 | 2.63 | 2.27 | 2.18 | 2.76 | 2.43 | |
| Human SummariesModel Category=Ground Truth2024.02 | 4.39 | 4.41 | 3.78 | 3.98 | 3.54 | 3.71 | 3.66 | |
| PlanSumModel Category=Pre-LLMs2024.02 | 1.86 | 1.94 | 1.6 | 1.38 | 1.52 | 1.59 | 1.56 |