Meta-review generation on Meta-Review Generation (test)
57.43FusionEvalPipeline-Ours
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Pipeline-OursBackbone LLM=GPT-42024.02 | 57.43 | 42.36 | 24.91 | 4.57 | 22.7 | |
| Pipeline-OursBackbone LLM=GPT-3.52024.02 | 55.96 | 39.5 | 28.92 | 5.52 | 16.13 | |
| Prompt-OursBackbone LLM=GPT-42024.02 | 53.62 | 41.98 | 28.02 | 6.57 | 25.51 | |
| Pipeline-OursBackbone LLM=LLaMA2-70B2024.02 | 52.8 | 36.82 | 26.41 | 4.48 | 23.71 | |
| Pipeline-OursBackbone LLM=LLaMA2-7B2024.02 | 52.68 | 38.35 | 19.39 | 4.12 | 17.37 | |
| Prompt-OursBackbone LLM=GPT-3.52024.02 | 51.4 | 39.88 | 29.56 | 6.95 | 26.69 | |
| Prompt-OursBackbone LLM=LLaMA2-70B2024.02 | 50.24 | 36.64 | 26.98 | 5.58 | 24.2 | |
| Prompt-OursBackbone LLM=LLaMA2-7B2024.02 | 50.18 | 38.07 | 27 | 6.86 | 24.59 | |
| Prompt-NaiveBackbone LLM=GPT-42024.02 | 50.14 | 35.42 | 27.16 | 6.63 | 24.78 | |
| Prompt-LLMBackbone LLM=GPT-3.52024.02 | 49.66 | 36.83 | 25.04 | 5.79 | 22.77 | |
| Prompt-LLMBackbone LLM=GPT-42024.02 | 48.9 | 40.54 | 27.49 | 6.03 | 24.75 | |
| Prompt-LLMBackbone LLM=LLaMA2-70B2024.02 | 48.53 | 36.4 | 16.6 | 3.13 | 14.63 | |
| Prompt-NaiveBackbone LLM=GPT-3.52024.02 | 48.35 | 38.44 | 28.22 | 6.63 | 25.36 | |
| Prompt-NaiveBackbone LLM=LLaMA2-70B2024.02 | 47.35 | 35.9 | 26.61 | 6.56 | 24.62 | |
| Prompt-NaiveBackbone LLM=LLaMA2-7B2024.02 | 46.85 | 35.89 | 25.94 | 6.04 | 23.57 | |
| Prompt-LLMBackbone LLM=LLaMA2-7B2024.02 | 46.83 | 32.49 | 23.88 | 4.5 | 21.59 |