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

Hallucination Detection on CoQA (AUPRC)

89.01AUPRC

Lyapunov Probes

32.662847.291461.9276.5486Mar 6, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
89.01
2026.03
88.3
2026.03
81.28
2026.03
80.67
2026.03
76.13
2026.03
72.25
2026.03
66.03
2026.03
65.36
2026.03
62.56
2026.03
61.13
2026.03
59.54
2026.03
53.5
2026.03
53.29
2026.03
52.4
2026.03
51.52
2026.03
50.35
2026.03
49.63
2026.03
37.13
2026.03
35.54
2026.03
34.83