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

Hallucination Detection on HotpotQA

0.928AUROC

PR

0.6002960.6853730.770450.855527Jul 22, 2025Sep 3, 2025Oct 16, 2025Nov 28, 2025Jan 10, 2026Feb 22, 2026Apr 7, 2026
Updated 10d ago

Evaluation Results

MethodLinks
2026.01
0.928
2026.04
0.928
2026.04
0.922
2026.04
0.918
2026.01
0.9151
2026.04
0.91
2026.01
0.9091
2026.01
0.9066
2026.04
0.905
2026.01
0.9025
2026.01
0.8904
2026.01
0.8903
2026.01
0.8903
2026.01
0.8816
2026.01
0.8781
2026.01
0.8781
2026.01
0.8769
2026.04
0.875
2026.04
0.871
2026.04
0.867
2026.01
0.8665
2026.01
0.8654
2026.01
0.8641
2026.01
0.8582
2026.01
0.8582
2026.04
0.856
2026.01
0.8545
2026.01
0.8545
2026.04
0.853
2026.01
0.8463
2026.01
0.8457
2026.01
0.8457
2026.01
0.8445
2026.04
0.842
2026.01
0.8411
2026.01
0.8376
2026.01
0.8354
2026.01
0.8319
2026.01
0.8319
2026.01
0.8293
2026.01
0.8293
2026.01
0.8248
2026.01
0.8223
2026.01
0.8223
2026.04
0.819
2026.04
0.801
2026.01
0.7988
2026.01
0.7988
2026.04
0.798
2025.07
0.7905
2025.07
0.7751
2025.07
0.7747
2026.04
0.774
2026.04
0.76
2026.01
0.7513
2026.04
0.751
2026.01
0.7451
2026.02
0.74
2026.01
0.7223
2026.01
0.7223
2026.01
0.7216
2025.07
0.7214
2026.04
0.715
2026.01
0.7111
2026.02
0.71
2025.07
0.6874
2026.04
0.682
2026.01
0.6808
2026.01
0.6808
2026.01
0.6806
2026.02
0.68
2026.04
0.677
2025.07
0.6729
2026.01
0.6714
2026.04
0.67
2026.04
0.661
2026.04
0.65
2026.01
0.6491
2026.04
0.647
2026.04
0.642
2026.01
0.6418
2026.01
0.6406
2026.02
0.64
2026.02
0.64
2026.02
0.64
2026.01
0.6395
2026.04
0.637
2026.01
0.6329
2026.01
0.6328
2026.01
0.6313
2026.02
0.63
2026.04
0.63
2026.04
0.627
2026.04
0.627
2026.01
0.6263
2026.04
0.625
2026.01
0.6216
2026.01
0.6206
2026.02
0.62
2026.01
0.6129
Showing 100 of 163 rows