Paired LLM Evaluation Resolution Analysis on OLL headline v1
27.5Unresolved Pair RatioFixed-n
Evaluation Results
| Method | Links | |
|---|---|---|
| Fixed-nProcedure=Fixed-n2026.05 | 27.5 | |
| Bonferroni / HolmProcedure=Bonferroni / Holm2026.05 | 35 | |
| Anytime-validProcedure=Anytime-valid2026.05 | 35 |