Fine-tuning LLMs on repeated sensitive data is claimed to raise privacy leakage to 60-75%, and four filters are said to cut leakage to 0% while keeping 94.7% of utility.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models
Fine-tuning LLMs on repeated sensitive data is claimed to raise privacy leakage to 60-75%, and four filters are said to cut leakage to 0% while keeping 94.7% of utility.