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

Hallucination Detection on HaluEval Dialogue latest (test)

84.88Accuracy

SkillAggregation

43.924854.557465.1975.8226Oct 14, 2024Jan 1, 2025Mar 21, 2025Jun 8, 2025Aug 26, 2025Nov 13, 2025Jan 31, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.10
84.88
2024.10
84.79
2024.10
84.22
2024.10
83.94
2024.10
82.97
2024.10
81.1
2024.10
81.06
2024.10
80.86
2024.10
80.83
2024.10
80.81
2024.10
80.22
2024.10
79.27
2024.10
78.78
2024.10
76.78
2024.10
76.28
2024.10
76.16
2026.01
49.1
2026.01
47.9
2026.01
47.1
2026.01
45.8
2026.01
45.8
2026.01
45.5