WatME: Towards lossless watermarking through lexical redundancy
Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of...
Saved in:
Main Authors: | CHEN, Liang, BIAN, Yatao, DENG, Yang, CAI, Deng, LI, Shuaiyi, ZHAO, Peilin, WONG, Kam-Fai |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9237 https://ink.library.smu.edu.sg/context/sis_research/article/10237/viewcontent/2024.acl_long.496.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Attack prompt generation for red teaming and defending large language models
by: DENG, Boyi, et al.
Published: (2023) -
Deep code comment generation with hybrid lexical and syntactical information
by: HU, Xing, et al.
Published: (2019) -
Large language models as source planner for personalized knowledge-grounded dialogues
by: WANG, Hongru, et al.
Published: (2023) -
Lossless watermarking considering the human visual system
by: Awrangjeb, M., et al.
Published: (2013) -
Laughter emotion recognition using gestures
by: De Jesus, Paulina Catya S.
Published: (2014)