Newest papers

HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models

Ke Zhu, Yanli Chen, Ling Xiong, Gejian Zhao, Hanzhou Wu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30601 · cited by 0 works (OpenAlex) · open-access PDF

Korean

텍스트 생성 애플리케이션에서 대형 언어 모델 (LLM)의 빠른 채택으로 인해 생성된 콘텐츠를 추적하고 사용에 대한 책임을 부여하는 것이 점점 더 어려워졌으며 출처, 저작권 보호 및 책임에 대한 우려를 제기합니다. 멀티비트 워터마킹은 생성된 텍스트에 멀티비트 출처 정보를 삽입함으로써 이러한 문제를 해결합니다. 생성 된 워터마킹을 삽입하는 동안 HiMark는 초기 후보 샘플링, 레이어 방식으로 워터마크 추출 정확성과 텍스트 품질 사이의 교환으로 인해 신뢰할 수있는 추출이 어려워집니다. 이러한 도전을 해결하기 위해 우리는 HiMark, LLM 생성 된 텍스트에 대한 계열적이고 제어 가능한 멀티비

Machine translation (Meta M2M100); the English original follows.

Abstract

With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated content and assign responsibility for its use, raising concerns about provenance, copyright protection, and accountability. Multi-bit watermarking addresses these issues by embedding multi-bit provenance information into generated text, but reliable extraction remains difficult due to sparse per-bit evidence and the trade-off between watermark-extraction accuracy and text quality. To deal with these challenges, we propose HiMark, a hierarchical and controllable multi-bit watermarking framework for LLM-generated text. During watermark embedding, HiMark uses a hierarchical candidate-control mechanism, including initial candidate sampling, layer-wise tournament elimination, support-based refinement, and support-threshold filtering. During watermark detection, a model-agnostic evidence aggregation mechanism computes multi-layer support evidence for each observed token, and then accumulates these token-level votes into the corresponding information for robust watermark extraction. Experiments show that HiMark improves watermark extraction accuracy while maintaining text quality, e.g., the watermark extraction accuracy is 90.01% under the paraphrasing attack when 32 bits were embedded within a text containing 300 tokens, demonstrating its effectiveness for provenance tracking.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Digital watermarking, Watermark, Computer science, TRACE (psycholinguistics), Embedding, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange