Abstractive Summarization on ACI-BENCH
0.12BLEUGPT-4
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-42023.11 | 0.12 | 0.2946 | 7 | |
| WizardLM-70B2023.11 | 0.1027 | 0.2866 | 5.84 | |
| Orca-2-13BSystem Message=Direct2023.11 | 0.0965 | 0.2987 | 5.36 | |
| Orca-2-7BSystem Message=Direct2023.11 | 0.0929 | 0.2903 | 5.29 | |
| ChatGPT2023.11 | 0.0755 | 0.2126 | 4.63 | |
| WizardLM-13B2023.11 | 0.0645 | 0.2396 | 6.35 | |
| LLAMA-2-Chat-70B2023.11 | 0.0641 | 0.2356 | 6.86 | |
| Orca-2-7BSystem Message=Cautious2023.11 | 0.058 | 0.2542 | 6.37 | |
| Orca-2-13BSystem Message=Cautious2023.11 | 0.0525 | 0.254 | 5.74 | |
| LLAMA-2-Chat-13B2023.11 | 0.0467 | 0.2147 | 7 | |
| Orca-1-13B2023.11 | 0.0336 | 0.1529 | 6.41 |