Robust and semantic-faithful post-hoc watermarking of text generated by black-box language models

Jifei HAO; Jipeng QIANG; Yi ZHU; Yun LI; Yunhao YUAN; Xiaocheng HU; Xiaoye OUYANG

doi:10.1007/s11704-024-40751-w

Front. Comput. Sci. ›› 2025, Vol. 19 ›› Issue (9) : 199357 DOI: 10.1007/s11704-024-40751-w

Artificial Intelligence

LETTER

Robust and semantic-faithful post-hoc watermarking of text generated by black-box language models

Author information +

History +

PDF (495KB)

Graphical abstract

Cite this article

Download citation ▾

Jifei HAO, Jipeng QIANG, Yi ZHU, Yun LI, Yunhao YUAN, Xiaocheng HU, Xiaoye OUYANG. Robust and semantic-faithful post-hoc watermarking of text generated by black-box language models. Front. Comput. Sci., 2025, 19(9): 199357 DOI:10.1007/s11704-024-40751-w

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Stokel-Walker C. ChatGPT listed as author on research papers: many scientists disapprove. Nature, 2023 , 613(7945): 620−621

[2]	L iebrenz M, S chleifer R, B uadze A, B hugra D, S mith A . Generating scholarly content with ChatGPT: ethical challenges for medical publishing. The Lancet Digital Health, 2023, 5( 3): e105–e106

[3]	Q iang J, Z hu S, L i Y, Z hu Y, Y uan Y, W u X . Natural language watermarking via paraphraser-based lexical substitution. Artificial Intelligence, 2023, 317: 103859

[4]	Mitchell E, Lee Y, Khazatsky A, Manning C D, Finn C. DetectGPT: zero-shot machine-generated text detection using probability curvature. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 24950–24962

[5]	Kirchenbauer J, Geiping J, Wen Y, Katz J, Miers I, Goldstein T. A watermark for large language models. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 17061–17084

[6]	Yang X, Chen K, Zhang W, Liu C, Qi Y, Zhang J, Fang H, Yu N. Watermarking text generated by black-box language models. 2023, arXiv preprint arXiv: 2305.08883

[7]	Yoo K, Ahn W, Jang J, Kwak N. Robust multi-bit natural language watermarking through invariant features. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 2092–2115

[8]	Campos R, Mangaravite V, Pasquali A, Jorge A M, Nunes C, Jatowt A. YAKE! Collection-independent automatic keyword extractor. In: Proceedings of the 40th European Conference on IR Research Advances in Information Retrieval. 2018, 806–810

[9]	Qiang J, Liu K, Li Y, Yuan Y, Zhu Y. ParaLS. Lexical substitution via pretrained paraphraser. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 3731–3746