SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A topic-guided watermarking scheme partitions the LLM vocabulary into topic-aligned token subsets and green-lists relevant tokens based on the input prompt to embed detectable marks while preserving text quality and improving robustness to attacks.
DEW creates a robust watermark for LLM text by applying vector-space operations to dual embeddings and hiding the signal via key-seeded random projections, showing improved detection after paraphrasing and translation.
citing papers explorer
-
SWAN: Semantic Watermarking with Abstract Meaning Representation
SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.
-
Topic-Based Watermarks for Large Language Models
A topic-guided watermarking scheme partitions the LLM vocabulary into topic-aligned token subsets and green-lists relevant tokens based on the input prompt to embed detectable marks while preserving text quality and improving robustness to attacks.
-
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
DEW creates a robust watermark for LLM text by applying vector-space operations to dual embeddings and hiding the signal via key-seeded random projections, showing improved detection after paraphrasing and translation.