List your company

Fact Verification on TruthfulQA

82.7Macro F1SEVA-GRPO (3B)
47.23656.44365.6574.857Jun 29, 2026

Evaluation results

MethodLinks
SEVA-GRPO (3B)Output format=struct, Size=3B2026.0682.7
SEVA-SFT (3B)Output format=struct, Size=3B2026.0672.1
MiniCheck-FT5Output format=binary2026.0659.5
GPT-4o-miniOutput format=struct2026.0648.6