List your company

Question Answering on DROP history

68.52F1 ScoreToken-Guard
41.604848.592455.5862.5676Jan 29, 2026

Evaluation results

MethodLinks
Token-Guard2026.0168.52
Self-RAG2026.0150.13
Self-Reflection2026.0147.48
BaseModel2026.0144.21
SELF-REFINE2026.0142.64