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

Hallucination Detection on TriviaQA

0.98AUROC

PCNET

0.858320.889910.92150.95309Aug 25, 2025Oct 9, 2025Nov 24, 2025Jan 9, 2026Feb 24, 2026Apr 11, 2026May 27, 2026
Updated 21h ago

Evaluation Results

MethodLinks
2026.05
0.98-------------96-----
2026.05
0.97-------------97-----
0.9587------------89.8------
2025.08
0.9565------------88.77------
2025.08
0.9545------------88.06------
2025.12
0.95-------------------
2026.05
0.95-------------93-----
2026.05
0.95-------------92-----
0.9482------------87.12------
0.9478------------86.52------
2025.08
0.9468------------86.01------
2025.08
0.946------------86.18------
2025.08
0.9457------------86.51------
2025.08
0.9448------------86.18------
0.943------------85.8------
2025.08
0.9426------------84.81------
2025.08
0.9401------------84------
2026.04
0.94-------------------
2026.01
0.9395-------------------
2025.08
0.9394------------84.91------
2025.08
0.9385------------84.18------
2026.04
0.935-------------------
2025.08
0.9306------------84.15------
0.93-------------------
2026.03
0.928-------------------
2026.04
0.928-------------------
2025.08
0.925------------80.02------
2026.04
0.9236-------95.37-----------
2026.04
0.9236-------95.37-----------
2025.08
0.9231------------79.75------
2025.08
0.9206------------78.83------
2025.08
0.9198------------81.38------
2026.04
0.918-------------------
2026.01
0.9162-------------------
2026.04
0.915-------------------
2026.03
0.913-------------------
2025.08
0.9109------------77.32------
2026.04
0.9106----0.828--------------
2026.03
0.9102-------91.02-----------
2026.05
0.91-------------90-----
2025.08
0.9097------------78.02------
2025.08
0.9093------------78.39------
2025.08
0.9075------------78.5------
2026.04
0.9066-------93.98-----------
2026.04
0.9066-------93.98-----------
2026.01
0.9052-------------------
2026.04
0.905----0.8245--------------
2025.08
0.9008------------77.04------
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-------------------
2025.08
0.8889------------60.32------
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--------------
2026.04
0.8875-------91.22-----------
2026.04
0.8875-------91.22-----------
2025.08
0.8865------------58.28------
2026.01
0.8854-------------------
2026.03
0.8842-------76.75-----------
2026.04
0.883-------------------
2026.05
0.8805-------------------
2026.05
0.8805-------------------
2026.05
0.88-------------87-----
2026.05
0.8799-------------------
2026.05
0.8799-------------------
2026.05
0.8782-------------------
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--------------
2025.08
0.8734------------75.43------
2026.01
0.8731-------------------
2026.05
0.8731-------------------
2026.04
0.873-------------------
2026.03
0.872-------------------
2026.01
0.8697-------------------
2026.04
0.868-------------------
2026.05
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-------------------
2026.05
0.863-------------------
Showing 100 of 861 rows
...