Introduces a 200-document benchmark and character-level R-Score for contextual PII redaction, with model evaluations and human agreement data showing the task remains unsolved.
Large Language Models Can Be Contextual Privacy Protection Learners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLMs exhibit 20-40% lower recall on ambiguous human names for PII detection, worsening under prompt injections, as shown via the new AmBench benchmark.
citing papers explorer
-
RedactionBench
Introduces a 200-document benchmark and character-level R-Score for contextual PII redaction, with model evaluations and human agreement data showing the task remains unsolved.
-
Can Large Language Models Really Recognize Your Name?
LLMs exhibit 20-40% lower recall on ambiguous human names for PII detection, worsening under prompt injections, as shown via the new AmBench benchmark.