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

Hallucination Detection on SciQ (AUROC)

64.8AUROC

EigenWD M1

-2.05785615.29947232.656850.014128Mar 17, 2026Mar 31, 2026Apr 14, 2026Apr 29, 2026May 13, 2026May 27, 2026Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
64.8
2026.03
63.98
2026.03
59.78
2026.03
59.16
2026.03
57.84
2026.03
49.21
2026.06
0.9663
2026.06
0.9548
2026.06
0.9263
2026.06
0.9263
2026.06
0.9257
2026.06
0.9247
2026.06
0.9189
2026.06
0.9051
2026.06
0.8992
2026.06
0.8663
2026.06
0.8663
2026.06
0.8604
2026.06
0.8604
2026.06
0.8563
2026.06
0.8563
2026.06
0.8539
2026.06
0.8521
2026.06
0.8421
2026.06
0.8411
2026.06
0.8001
2026.06
0.8001
2026.06
0.7988
2026.06
0.7977
2026.06
0.7905
2026.06
0.7895
2026.06
0.7877
2026.06
0.7877
2026.06
0.782
2026.06
0.7781
2026.06
0.7708
2026.06
0.7564
2026.06
0.7498
2026.06
0.7498
2026.06
0.7465
2026.06
0.7096
2026.06
0.7084
2026.06
0.7046
2026.06
0.6904
2026.06
0.6904
2026.06
0.6877
2026.06
0.6839
2026.06
0.6709
2026.06
0.6678
2026.06
0.6675
2026.06
0.6615
2026.06
0.6612
2026.06
0.6518
2026.06
0.6456
2026.06
0.6367
2026.06
0.6316
2026.06
0.6287
2026.06
0.6269
2026.06
0.6186
2026.06
0.6165
2026.06
0.6122
2026.06
0.6067
2026.06
0.5968
2026.06
0.5927
2026.06
0.5916
2026.06
0.5906
2026.06
0.5885
2026.06
0.5831
2026.06
0.5796
2026.06
0.5788
2026.06
0.5742
2026.06
0.5689
2026.06
0.561
2026.06
0.5598
2026.06
0.5412
2026.06
0.5361
2026.06
0.536
2026.06
0.5285
2026.06
0.5152
2026.06
0.5136