Event Argument Extraction on WikiEvents Wiki2Wiki
47.62Overall F1Ours (Qwen)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Ours (Qwen)Backbone=Qwen2026.03 | 47.62 | 47.39 | 47.82 | |
| Ours (LLaMA)Backbone=LLaMA2026.03 | 46.96 | 47.83 | 46.19 | |
| Bart-Gen2026.03 | 40.82 | 48.11 | 32.68 | |
| TabEAE2026.03 | 30.97 | 37.19 | 28.84 | |
| HMPEAE2026.03 | 30.2 | 38.43 | 27.48 | |
| PAIE2026.03 | 24.42 | 23.58 | 23.57 | |
| DEEIA2026.03 | 22.51 | 34.11 | 19.48 | |
| SCPRG2026.03 | 21.9 | 45.8 | 11.89 | |
| EEQA2026.03 | 21.5 | 23.05 | 14 | |
| Distar2026.03 | 17.51 | 2.72 | 20.18 | |
| TSAR2026.03 | 13.95 | 14.4 | 13.86 | |
| DS-R1CoT=false2026.03 | 12.84 | — | — | |
| DS-V3CoT=false2026.03 | 11.6 | — | — | |
| GPT-4oCoT=false2026.03 | 11.36 | — | — | |
| LLaMA-3.1CoT=false2026.03 | 10.55 | — | — | |
| DS-R1CoT=true2026.03 | 10.4 | — | — | |
| ZSTL2026.03 | 9.97 | — | — | |
| GPT-4oCoT=true2026.03 | 9.65 | — | — | |
| LLaMA-3.1CoT=true2026.03 | 8.87 | — | — | |
| DS-V3CoT=true2026.03 | 8.62 | — | — | |
| Phi-4CoT=false2026.03 | 7.3 | — | — | |
| MixtralCoT=false2026.03 | 6.34 | — | — | |
| Gemma-1.1CoT=false2026.03 | 6.31 | — | — | |
| MixtralCoT=true2026.03 | 6.23 | — | — | |
| Phi-4CoT=true2026.03 | 5.78 | — | — | |
| Gemma-1.1CoT=true2026.03 | 4.78 | — | — |