Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation

2025-04-16 · Shizhan Cai, Liang Ding, DaCheng Tao

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and ensuring robust detection against various attacks. To address these issues, we propose a novel watermarking scheme that improves both detectability and text quality by introducing a cumulative watermark entropy threshold. Our approach is compatible with and generalizes existing sampling functions, enhancing adaptability. Experimental results across multiple LLMs show that our scheme significantly outperforms existing methods, achieving over 80\% improvements on widely-used datasets, e.g., MATH and GSM8K, while maintaining high detection accuracy.

📄 PDF Abstract BibTeX arXiv:2504.12108

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KMathText Generation

dgMARK: Decoding-Guided Watermarking for Diffusion Language Models

2026-01-30 · Pyo Min Hong, Albert No arxiv

We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor wo…

CODE ACROSTIC: Robust Watermarking for Code Generation

2025-12-14 · Li Lin, Siyuan Xin, Yang Cao, Xiaochun Cao arxiv

Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contai…

Code Generation

WorldCup Sampling for Multi-bit LLM Watermarking

2026-02-02 · Yidan Wang, Yubing Ren, Yanan Cao, Li Guo arxiv

As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenan…

Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability

2026-07-11 · Licheng Yu, Aiwei Liu, Songze Li arxiv

With the rapid development of Large Language Models (LLMs), text watermarking has emerged as a crucial technique for identifying machine-generated content. However, directly applying existing logits-based watermarking me…

Code Generation

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts

2025-09-09 · Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng 외 arxiv

As large language models (LLMs) are adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitig…