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.

翻译：随着大语言模型生成的文本日益接近人类水平，水印技术为超越单纯检测的可信溯源提供了前景广阔的解决方案。尽管多比特水印能够实现更丰富的来源编码，现有方法主要通过种子驱动引导来扩展零比特方案，导致间接信息流、有限有效容量和次优解码性能。本文提出WorldCup——一种面向大语言模型的多比特水印框架，该框架将采样过程视为天然通信信道，并通过互补信号引导的分层竞争机制，将信息比特直接嵌入词汇选择过程。此外，WorldCup进一步采用熵感知调制以保持生成质量，并通过置信感知解码支持鲁棒信息恢复。综合实验表明，WorldCup在容量、可检测性、鲁棒性、文本质量与解码效率之间实现了出色平衡，持续超越现有基线方法，为未来大语言模型水印研究奠定了坚实基础。