STAMP detects dataset membership in LLMs by comparing model perplexity on a publicly released watermarked rephrasing against private watermarked rephrasings of the same documents.
URL https://aclanthology.org/W01-0500
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
STAMP detects dataset membership in LLMs by comparing model perplexity on a publicly released watermarked rephrasing against private watermarked rephrasings of the same documents.