Multi-class BERT outperforms multi-label BERT for CVE-to-CWE mapping, but the gap narrows with fewer classes and threshold tuning, while dominant errors follow the CWE hierarchy across all models.
Proceedings of NAACL-HLT pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors
Multi-class BERT outperforms multi-label BERT for CVE-to-CWE mapping, but the gap narrows with fewer classes and threshold tuning, while dominant errors follow the CWE hierarchy across all models.