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.
The Science of Detecting LLM-Generated Text.Commun
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
An adversarial methodology generates a multilingual cross-platform dataset of paired human-AI social messages, and models trained on it outperform prior detectors on real-world out-of-distribution data.
Experiments on 250 participants show LLM-assisted survey responses range from under 10% on Prolific to over 80% on Mechanical Turk, with identifiable characteristics and partial mitigation effects.
citing papers explorer
-
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.
-
Adversarial Creation and Detection of AI-Generated Social Bot Content
An adversarial methodology generates a multilingual cross-platform dataset of paired human-AI social messages, and models trained on it outperform prior detectors on real-world out-of-distribution data.