An MLP trained on LLM internal states predicts Rouge-L-defined literal copying leakage with high accuracy, but not paraphrase-level leakage.
Title resolution pending
1 Pith paper cite this work, alongside 39 external citations. Polarity classification is still indexing.
1
Pith paper citing it
39
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
An MLP trained on LLM internal states predicts Rouge-L-defined literal copying leakage with high accuracy, but not paraphrase-level leakage.