WorldCup Sampling for Multi-bit LLM Watermarking

As large language models (LLMs) generate increasingly human-like text, watermarking offers a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenance encoding, existing methods largely extend zero-bit schemes through seed-driven steering, leading to indirect information flow, limited effective capacity, and suboptimal decoding. In this paper, we propose WorldCup, a multi-bit watermarking framework for LLMs that treats sampling as a natural communication channel and embeds message bits directly into token selection via a hierarchical competition mechanism guided by complementary signals. Moreover, WorldCup further adopts entropy-aware modulation to preserve generation quality and supports robust message recovery through confidence-aware decoding. Comprehensive experiments show that WorldCup achieves a strong balance across capacity, detectability, robustness, text quality, and decoding efficiency, consistently outperforming prior baselines and laying a solid foundation for future LLM watermarking studies.

Key Contributions

• WorldCup hierarchical competition mechanism that embeds multi-bit messages directly into LLM token selection, treating sampling as a communication channel
• Entropy-aware modulation to preserve text generation quality during watermarking
• Confidence-aware decoding for robust multi-bit message recovery from watermarked text

🛡️ Threat Analysis

Details

Similar Papers