SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
Semstamp: A semantic watermark with paraphrastic robustness for text generation.arXiv preprint arXiv:2310.03991
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
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.
Watermarking enables entity-level attribution and monitoring via signal aggregation across outputs, even in zero-bit designs, revealing a fundamental tension with attribution goals.
TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.
citing papers explorer
-
SLAM: Structural Linguistic Activation Marking for Language Models
SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
-
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.
-
Watermarking Should Be Treated as a Monitoring Primitive
Watermarking enables entity-level attribution and monitoring via signal aggregation across outputs, even in zero-bit designs, revealing a fundamental tension with attribution goals.
-
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.