Query-based Summarization on QMSum Golden v1 (test)
40.85ROUGE-1IDEALLoRA
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| IDEALLoRALC=3K2024.07 | 40.85 | 16.89 | 29.67 | 36.66 | 87.83 | |
| IDEALPAdapterLC=3K2024.07 | 40.79 | 17.24 | 29.64 | 36.55 | 87.8 | |
| LoraLC=3K2024.07 | 40.69 | 16.11 | 28.84 | 36.18 | 87.71 | |
| PAdapterLC=3K2024.07 | 39.41 | 15.77 | 28.18 | 34.98 | 87.54 | |
| Bart-largeLC=1K2024.07 | 38.49 | 14.26 | 25.25 | 33.75 | 86.38 | |
| ChatGPT2024.07 | 36.83 | 12.78 | 24.23 | 24.19 | — | |
| HMNet2024.07 | 36.06 | 11.36 | — | 31.27 | — | |
| IDEALPromptLC=3K2024.07 | 35.58 | 13.75 | 25.33 | 31.52 | 86.73 | |
| PromptLC=3K2024.07 | 34.81 | 13.33 | 24.99 | 30.73 | 86.69 | |
| GPT-4OLC=3K2024.07 | 33.46 | 10.22 | 20.59 | 30.18 | 85.87 | |
| Llama3.1-8BLC=3K2024.07 | 20.51 | 6.76 | 13.94 | 18.44 | 82.39 |