Aspect-based Summarization on CovidET v1 (test)
29.62ROUGE-1IDEALLoRA
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| IDEALLoRALC=1K2024.07 | 29.62 | 8.84 | 23.4 | 24.06 | 89.12 | |
| IDEALPAdapterLC=1K2024.07 | 29.51 | 8.78 | 23.21 | 23.8 | 89.07 | |
| PAdapterLC=1K2024.07 | 29.37 | 8.84 | 23.2 | 23.86 | 89.06 | |
| PromptLC=1K2024.07 | 29.18 | 8.77 | 23.64 | 24.15 | 89.2 | |
| IDEALPromptLC=1K2024.07 | 29.1 | 9.01 | 23.65 | 24.18 | 89.26 | |
| LoraLC=1K2024.07 | 29 | 8.43 | 22.79 | 23.43 | 89 | |
| Bart-largeLC=1K2024.07 | 27.54 | 7.72 | 21.66 | 22.24 | 88.61 | |
| LED-base-OASumLC=4K2024.07 | 25.61 | 6.58 | — | 20.45 | — | |
| ChatGPT2024.07 | 20.81 | 3.99 | 15.35 | 15.36 | — | |
| GPT-4OLC=1K2024.07 | 17.01 | 3.35 | 13.18 | 13.24 | 87.33 | |
| Llama3.1-8BLC=1K2024.07 | 12.85 | 2.12 | 9.32 | 11.04 | 84.55 |