WorldCup is a new multi-bit LLM watermarking framework that models token sampling as a communication channel and uses hierarchical competition with entropy-aware modulation for robust message embedding and recovery.
• Word-S-BERT (ratio = ρ): Randomly substitutes a proportion ρ of words with context-aware synonyms generated by a BERT-based (Devlin et al., 2019) model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WorldCup Sampling for Multi-bit LLM Watermarking
WorldCup is a new multi-bit LLM watermarking framework that models token sampling as a communication channel and uses hierarchical competition with entropy-aware modulation for robust message embedding and recovery.