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

Hallucination Detection on PopQA (AUPRC)

67.08AUPRC

Lyapunov Probes

7.823.1938.5853.97Mar 6, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
67.08
2026.03
64.41
2026.03
64.02
2026.03
63.37
2026.03
61.87
2026.03
61.23
2026.03
60.77
2026.03
60.48
2026.03
27.02
2026.03
21.23
2026.03
20.22
2026.03
20.13
2026.03
18.42
2026.03
18.26
2026.03
16.53
2026.03
15.13
2026.03
13.79
2026.03
13.76
2026.03
12.04
2026.03
10.08