Skip to content
Search
paperSeptember 2026Unreviewed

A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content

Zhongli Fang, Yiran Chen, Lingyun Zhang, Yu Liu, Ping Chen, Xiaoyan Sun, Jun Dai

View resourcePDF

Abstract

Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creating serious risks in critical areas such as food safety reporting. To protect the integrity and traceability of AI-generated content, this paper introduces ToSS (Token Oriented Repartitioning and Strategic Selection), a reliable authentication method using adaptive dual watermarking. The key innovation of ToSS is its dual watermark encoding approac

Categories

Watermarking

Cite

@misc{fang2026trustworthy,
  title = {{A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content}},
  author = {Zhongli Fang and Yiran Chen and Lingyun Zhang and Yu Liu and Ping Chen and Xiaoyan Sun and Jun Dai},
  year = {2026},
  month = sep,
  eprint = {2609.06708},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.06708}
}