List your company

Semantic Hijacking on MultiWOZ Semantic Hijacking 2.2

10Vanilla APAVanilla
9.59.751010.25Apr 27, 2026

Evaluation results

MethodLinks
VanillaModel Pair (Architect / Executive)=GPT 5.4 / 5.4 mini2026.0410———
SSRPModel Pair (Architect / Executive)=GPT 5.4 / 5.4 mini2026.04—71.671,5001