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

Hallucination Detection on SQuAD v2.0

98AUROC

PCNET

39.7654.887085.12May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
9897
2026.05
9897
2026.05
9897
2026.05
9796
2026.05
9796
2026.05
9591
2026.05
9090
2026.05
8280
2026.05
6471
2026.05
6267
2026.05
6268
2026.05
6168
2026.05
6169
2026.05
6167
2026.05
5868
2026.05
5868
2026.05
5868
2026.05
5867
2026.05
5767
2026.05
4267