Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hallucination Regression on PHOENIX 2014T

-0.189Pearson

Perplexity

-0.66844-0.54397-0.4195-0.29503Oct 21, 2025
Updated 1d ago

Evaluation Results

MethodLinks
2025.10
-0.189-0.2290.296
2025.10
-0.275-0.2730.342
2025.10
-0.344-0.3080.43
2025.10
-0.4-0.5420.609
2025.10
-0.458-0.40.493
2025.10
-0.468-0.5440.625
2025.10
-0.61-0.5740.637
2025.10
-0.612-0.5780.637
2025.10
-0.623-0.590.65
2025.10
-0.65-0.6130.675