Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factuality Detection on TriviaQA, HotpotQA, and CSQA
Loading...
72.9
Average AUROC
DynHD
57.612
61.581
65.55
69.519
Mar 17, 2026
Average AUROC
Updated 2mo ago
Evaluation Results
Method
Method
Links
Average AUROC
DynHD
Method Category=Trajec...
2026.03
72.9
TraceDet
Method Category=Trajec...
2026.03
66.3
TSV
Method Category=Latent...
2026.03
61.3
CCS
Method Category=Latent...
2026.03
58.2
Feedback
Search any
task
Search any
task
