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.
Towards possibilities & impossibilities of ai-generated text detection: A survey.arXiv preprint arXiv:2310.15264
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
AI-generated text detectors achieve high benchmark accuracy by exploiting unstable dataset-specific linguistic features, as evidenced by cross-domain degradation and differing SHAP explanations across corpora.
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
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.
-
Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy
AI-generated text detectors achieve high benchmark accuracy by exploiting unstable dataset-specific linguistic features, as evidenced by cross-domain degradation and differing SHAP explanations across corpora.
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.