List your company

Incorrectness detection on SQuAD

74.2AUC ScoreSHADE
56.62461.18765.7570.313Apr 21, 2026

Evaluation results

MethodLinks
SHADEn (sampling budget)=82026.0474.268.1
Hb Hybridn (sampling budget)=82026.0474.168
NumSetsn (sampling budget)=82026.0473.967.5
NumSetsn (sampling budget)=102026.0473.568.3
SHADEn (sampling budget)=102026.0473.367.9
Hb Hybridn (sampling budget)=102026.0473.267.7
Hb Pluginn (sampling budget)=102026.0473.168.3
Hb Pluginn (sampling budget)=82026.0472.767.4
SHADEn (sampling budget)=52026.0471.166.6
Hb Hybridn (sampling budget)=52026.047166.5
NumSetsn (sampling budget)=52026.047163.2
|S| Hybridn (sampling budget)=82026.0470.168.2
Hb Pluginn (sampling budget)=52026.0469.964.4
|S| Hybridn (sampling budget)=52026.0469.668.2
|S| Hybridn (sampling budget)=102026.0467.765.4
KLEn (sampling budget)=82026.0461.863.5
DSEn (sampling budget)=52026.0461.157.1
KLEn (sampling budget)=102026.0461.164.4
DSEn (sampling budget)=102026.0460.359.1
KLEn (sampling budget)=52026.045962.3
DSEn (sampling budget)=82026.0457.357.6