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

Hallucination Detection on TriviaQA

0.95AUROC

SAPLMA

0.8150080.8500540.88510.920146Feb 6, 2025Apr 18, 2025Jun 29, 2025Sep 9, 2025Nov 20, 2025Jan 31, 2026Apr 13, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
0.95-----------
2026.04
0.94-----------
2026.01
0.9395-----------
2026.04
0.935-----------
2025.12
0.93-----------
2026.03
0.928-----------
2026.04
0.928-----------
2026.04
0.918-----------
2026.01
0.9162-----------
2026.04
0.915-----------
2026.03
0.913-----------
2026.04
0.9106----0.828------
2026.03
0.9102-------91.02---
2026.01
0.9052-----------
2026.04
0.905----0.8245------
2026.03
0.897-----------
2026.04
0.897-----------
2026.01
0.8967-----------
2026.04
0.895-----------
2026.03
0.8942-------88.43---
2025.12
0.893---0.9770.6010.984-----
2025.12
0.891---0.9370.7270.961-----
2026.01
0.8896-----------
2026.01
0.8886-----------
2026.03
0.8882-------88.33---
2026.03
0.8882-------86.54---
2026.01
0.888-----------
2026.04
0.888-----------
2026.04
0.888----0.8113------
2026.01
0.8854-----------
2026.03
0.8842-------76.75---
2026.04
0.883-----------
2026.04
0.878-----------
2026.04
0.877-----------
2026.01
0.8745-----------
2026.04
0.874-----------
2026.04
0.874-----------
2026.04
0.8735----0.8------
2026.01
0.8731-----------
2026.04
0.873-----------
2026.03
0.872-----------
2026.01
0.8697-----------
2026.04
0.868-----------
2026.04
0.867-----------
2026.04
0.867-----------
2026.03
0.866-----------
2026.04
0.866-----------
2026.04
0.866-----------
2026.01
0.8657-----------
2026.01
0.8654-----------
2026.04
0.865-----------
2026.03
0.8632-------77.65---
2026.04
0.863-----------
2026.04
0.8614----0.7786------
2026.04
0.861-----------
2026.04
0.86-----------
2026.04
0.859-----------
2026.01
0.8573-----------
2025.12
0.856---0.9480.6650.96-----
2026.03
0.855-----------
2026.01
0.8548-----------
2026.04
0.8531----0.7863------
2026.03
0.85-----------
2026.04
0.85-----------
2025.12
0.848---0.930.5770.955-----
2026.01
0.8466-----------
2026.03
0.8443-------80.05---
2026.04
0.844-----------
2026.01
0.8436-----------
2026.01
0.8436-----------
2026.01
0.8422-----------
2026.01
0.8421-----------
2026.01
0.8413-----------
2026.01
0.8412-----------
2026.01
0.8403-----------
2026.01
0.8393-----------
2026.04
0.837-----------
2026.03
0.8363-------74.45---
2026.01
0.8357-----------
2026.01
0.8357-----------
2026.03
0.835-----------
2026.04
0.835-----------
2026.04
0.835-----------
2026.04
0.833-----------
2026.01
0.8313-----------
2026.01
0.8313-----------
2026.04
0.831-----------
2026.04
0.831----0.852------
2026.04
0.829----0.7984------
2025.12
0.827---0.030.4570.023-----
2026.03
0.827-----------
2026.04
0.827-----------
2026.04
0.827-----------
2026.03
0.8263-------71.56---
2026.04
0.826-----------
2026.01
0.8247-----------
2026.04
0.824-----------
2026.03
0.8233-------64.87---
2026.01
0.821-----------
2025.02
0.8202-----------
Showing 100 of 516 rows