Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Open-ended generation on TruthfulQA double info 1.0 (test)

68.4True Score

TACS-T

52.2856.46560.6564.835Mar 12, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.03
68.461.1
2024.03
64.558.9
2024.03
62.157
2024.03
58.454.2
2024.03
58.453.5
2024.03
55.452.5
2024.03
52.950.2