Question Answering on Wikipedia events 2024-2025 (test)
3.78Standing Q_t^bgNo Wiki
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| No Wikimode=direct LLM, N=1852026.06 | 3.78 | 3.81 | 3.8 | |
| Online WiCERsignal=AER, N=1192026.06 | 3.67 | 4.62 | 4.57 | |
| FIFOmode=recency only, N=2322026.06 | 3.5 | 4.77 | 4.74 | |
| Oraclemode=GT labels, N=2322026.06 | 3.5 | 4.77 | 4.74 | |
| Static Wikimode=baseline, N=1852026.06 | 3.36 | 4.64 | 4.14 |