Ke Zhu, Yanli Chen, Ling Xiong, Gejian Zhao, Hanzhou Wu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30601 · open-access PDF
テキスト生成アプリケーションにおける大規模言語モデル(LLM)の迅速な採用により、生成されたコンテンツを追跡し、その使用に責任を割り当てることがますます困難になり、出身地、著作権保護、責任に関する懸念が生じています。Multi-bit watermarkingは、生成されたテキストに複数の出身地情報を埋め込むことで、これらの問題に対処しますが、信頼性の高い抽出は、ビット当たりの証拠が少ないことと、ウォーターマーク抽出の正確性とテキストの品質の間のバランスによって困難です。
Machine translation (Meta M2M100); the English original follows.
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 co
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30601, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange