Research map / Large language models / Language, safety and interpretability
Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
Joeun Kim, HoEun Kim, Dongsup Jin, Young-Sik Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a longer BCH codeword (31,6,7) instead of (15,5,3) (ablation) | BREW · C4 OPT-1.3B 5% insertion-like substitution | FPR: 0.945 -> 0.085 | Improved |
| use a longer BCH codeword (31,6,7) instead of (15,5,3) (ablation) | BREW · C4 OPT-1.3B 5% insertion-like substitution | TPR: 0.990 -> 0.930 | Hurt |
| use an even longer BCH codeword (63,7,15) instead of (31,6,7) (ablation) | BREW · C4 OPT-1.3B 5% insertion-like substitution | TPR: 0.930 -> 0.710 | Hurt |
| use an even longer BCH codeword (63,7,15) instead of (31,6,7) (ablation) | BREW · C4 OPT-1.3B 5% insertion-like substitution | FPR: 0.085 -> 0.000 | Improved |
| use a longer BCH codeword (31,6,7) instead of (15,5,3) (ablation) | BREW · C4 OPT-1.3B 10% insertion-like substitution | FPR: 0.930 -> 0.110 | Improved |
| use a longer BCH codeword (31,6,7) instead of (15,5,3) (ablation) | BREW · C4 OPT-1.3B 10% insertion-like substitution | TPR: 1.000 -> 0.710 | Hurt |
| use an even longer BCH codeword (63,7,15) instead of (31,6,7) (ablation) | BREW · C4 OPT-1.3B 10% insertion-like substitution | TPR: 0.710 -> 0.305 | Hurt |
| use an even longer BCH codeword (63,7,15) instead of (31,6,7) (ablation) | BREW · C4 OPT-1.3B 10% insertion-like substitution | FPR: 0.110 -> 0.005 | Improved |
| apply a rejection threshold to the ECC-based baseline extractor | RS ECC-based baseline · synonym substitution ROC | TPR vs FPR | No clear effect |
Closest papers by meaning
- Robust Multi-bit Text Watermark with LLM-based Paraphrasers (ICML 2025 · similarity 0.90)
- BiMark: Unbiased Multilayer Watermarking for Large Language Models (ICML 2025 · similarity 0.90)
- Majority Bit-Aware Watermarking for Large Language Models (NeurIPS 2026 · similarity 0.89)
- MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages (NeurIPS 2026 · similarity 0.89)
- ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport (NeurIPS 2026 · similarity 0.88)
- PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
