Multiple-type control summarization on CNNDM (test)
0.3885ROUGE-1GPT-M Prompt
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-M PromptModel=GPT-M, Setting=Prompt2024.06 | 0.3885 | 0.1593 | 0.3848 | 0.6302 | 0.2132 | |
| GPT-M Prompt+filterModel=GPT-M, Setting=Prompt+filter2024.06 | 0.3885 | 0.1729 | 0.3768 | 0.6248 | 0.1121 | |
| GPT-L Prompt+filterModel=GPT-L, Setting=Prompt+filter2024.06 | 0.3875 | 0.1685 | 0.3823 | 0.6285 | 0.0334 | |
| GPT-L Prompt+RL+filterModel=GPT-L, Setting=Prompt+RL+filter2024.06 | 0.387 | 0.1652 | 0.3839 | 0.6298 | 0.0322 | |
| GPT-M Prompt+RLModel=GPT-M, Setting=Prompt+RL2024.06 | 0.383 | 0.1589 | 0.3929 | 0.629 | 0.0659 | |
| GPT-L PromptModel=GPT-L, Setting=Prompt2024.06 | 0.3827 | 0.1637 | 0.3892 | 0.6309 | 0.0689 | |
| GPT-L Prompt+RLModel=GPT-L, Setting=Prompt+RL2024.06 | 0.3823 | 0.1642 | 0.3886 | 0.6306 | 0.0662 | |
| GPT-S Prompt+filterModel=GPT-S, Setting=Prompt+filter2024.06 | 0.3804 | 0.1629 | 0.3712 | 0.6205 | 0.1057 | |
| GPT-M Prompt+RL+filterModel=GPT-M, Setting=Prompt+RL+filter2024.06 | 0.3783 | 0.1689 | 0.372 | 0.6191 | 0.0498 | |
| GPT-S PromptModel=GPT-S, Setting=Prompt2024.06 | 0.3776 | 0.1558 | 0.3805 | 0.6232 | 0.1816 | |
| GPT-S Prompt+RLModel=GPT-S, Setting=Prompt+RL2024.06 | 0.3752 | 0.1531 | 0.3879 | 0.6242 | 0.1429 | |
| GPT-S Prompt+RL+filterModel=GPT-S, Setting=Prompt+RL+filter2024.06 | 0.3748 | 0.1601 | 0.372 | 0.6188 | 0.0706 |