List your company

Hallucination Detection on Clinical Hallucination E4-level (test)

0.831F1 Score (E4)Qwen3-14B
0.542920.617710.69250.76729May 5, 2026

Evaluation results

MethodLinks
Qwen3-14BModel Configuration=Curated FT2026.050.8310.9090.765
Qwen3-14BModel Configuration=Original FT2026.050.8030.7480.867
Qwen3-PlusModel Configuration=API2026.050.7910.7450.842
Qwen3-14BModel Configuration=Base2026.050.5540.430.779