Timeline Summarization on T17 (test)
12AR-1DATEWISE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DATEWISE2026.06 | 12 | 3.5 | 54.4 | |
| SDF2026.06 | 12 | 3.5 | 55.3 | |
| NTS-CoT2026.06 | 11.6 | 3.2 | 54.1 | |
| One-shotPrompting=One-shot2026.06 | 11 | 2.8 | 51.3 | |
| MARTSCHAT2026.06 | 10.5 | 3 | 54.4 | |
| EGC2026.06 | 10.3 | 2.4 | 55 | |
| Zero-shotPrompting=Zero-shot2026.06 | 9.7 | 2.7 | 50.4 | |
| LLM-TLS2026.06 | 9.4 | 2.4 | 51.2 | |
| STEEN2026.06 | 9.3 | 2.4 | 51.2 | |
| Standard-CotPrompting=Chain-of-Thought2026.06 | 8.9 | 2.5 | 52.1 | |
| CLUST2026.06 | 8.2 | 2 | 40.7 |