List your company

Question Answering on TruthfulQA (Corr, Incorr, NΔ)

96.81Correlation ScoreMAUVE
-34.7916-0.625833.5467.7058May 26, 2026

Evaluation results

MethodLinks
MAUVE2026.0596.8186.610.21
BERTScore2026.0583.881.292.51
EmbSimrescaled to [0, 1]=true2026.0570.7763.113.83
SimCSErescaled to [0, 1]=true2026.0568.9855.776.61
MATCHArescaled to [0, 1]=true2026.0562.515.8523.33
R1-F12026.0545.1238.876.25
METEOR2026.0542.0833.68.48
RL-F12026.0540.7235.784.94
R2-F12026.0524.421.532.87
BLEURTrescaled to [0, 1]=true2026.05-29.73-63.4616.87