Plain Summarization on PLOS
47.27ROUGE-1Llama-3.1-8B-Instruct
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Llama-3.1-8B-InstructRevision Stage=Initial Summary2026.04 | 47.27 | 86.51 | 18.74 | 13.69 | 17.05 | 64.8 | 49.67 | |
| GPT-4oRevision Stage=Initial Summary2026.04 | 46.85 | 86.91 | 17.73 | 14.25 | 18.72 | 65.38 | 55.48 | |
| GPT-4oRevision Stage=Round 1, Revision Method=NRLB2026.04 | 45.12 | 86.61 | 13.37 | 13.21 | 15.86 | 71.35 | 67.12 | |
| Llama-3.1-8B-InstructRevision Stage=Round 1, Revision Method=NRLB2026.04 | 44.43 | 86 | 16.55 | 12.67 | 14.54 | 67.21 | 49.17 | |
| GPT-4oRevision Stage=Round 2, Revision Method=NRLB2026.04 | 42.77 | 86.29 | 10.94 | 12.56 | 13.96 | 74.67 | 72.93 | |
| Llama-3.1-8B-InstructRevision Stage=Round 2, Revision Method=NRLB2026.04 | 41.64 | 85.43 | 15.21 | 12.06 | 13.2 | 66.68 | 50.86 | |
| Qwen3-8BRevision Stage=Initial Summary2026.04 | 41.62 | 85.78 | 19.12 | 15.04 | 20.86 | 62.49 | 44.48 | |
| Qwen3-8BRevision Stage=Round 1, Revision Method=NRLB2026.04 | 37.55 | 85.33 | 14.12 | 13.61 | 16.54 | 71.62 | 48.88 | |
| Qwen3-8BRevision Stage=Round 2, Revision Method=NRLB2026.04 | 36.03 | 84.96 | 12.46 | 13.15 | 15.14 | 72.6 | 53.81 |