Domain-aware LLM prompting detects PII in math tutoring transcripts with much higher precision than generic tools, on a new benchmark built by LLM-aided surrogate annotation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset
Domain-aware LLM prompting detects PII in math tutoring transcripts with much higher precision than generic tools, on a new benchmark built by LLM-aided surrogate annotation.