A context-aware GPT-4o prompt detects personal columns more accurately than Presidio and CASSED on real-world structured datasets, but the causal role of context is not isolated by an ablation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detection of Personal Data in Structured Datasets Using a Large Language Model
A context-aware GPT-4o prompt detects personal columns more accurately than Presidio and CASSED on real-world structured datasets, but the causal role of context is not isolated by an ablation.