MarkLLM: An Open-Source Toolkit for LLM Watermarking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912087332093952 |
|---|---|
| author | Pan, Leyi Liu, Aiwei He, Zhiwei Gao, Zitian Zhao, Xuandong Lu, Yijian Zhou, Binglin Liu, Shuliang Hu, Xuming Wen, Lijie King, Irwin Yu, Philip S. |
| author_facet | Pan, Leyi Liu, Aiwei He, Zhiwei Gao, Zitian Zhao, Xuandong Lu, Yijian Zhou, Binglin Liu, Shuliang Hu, Xuming Wen, Lijie King, Irwin Yu, Philip S. |
| contents | LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of LLM watermarking algorithms, their intricate mechanisms, and the complex evaluation procedures and perspectives pose challenges for researchers and the community to easily experiment with, understand, and assess the latest advancements. To address these issues, we introduce MarkLLM, an open-source toolkit for LLM watermarking. MarkLLM offers a unified and extensible framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access. Furthermore, it enhances understanding by supporting automatic visualization of the underlying mechanisms of these algorithms. For evaluation, MarkLLM offers a comprehensive suite of 12 tools spanning three perspectives, along with two types of automated evaluation pipelines. Through MarkLLM, we aim to support researchers while improving the comprehension and involvement of the general public in LLM watermarking technology, fostering consensus and driving further advancements in research and application. Our code is available at https://github.com/THU-BPM/MarkLLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10051 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MarkLLM: An Open-Source Toolkit for LLM Watermarking Pan, Leyi Liu, Aiwei He, Zhiwei Gao, Zitian Zhao, Xuandong Lu, Yijian Zhou, Binglin Liu, Shuliang Hu, Xuming Wen, Lijie King, Irwin Yu, Philip S. Cryptography and Security Computation and Language 68T50 I.2.7 LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of LLM watermarking algorithms, their intricate mechanisms, and the complex evaluation procedures and perspectives pose challenges for researchers and the community to easily experiment with, understand, and assess the latest advancements. To address these issues, we introduce MarkLLM, an open-source toolkit for LLM watermarking. MarkLLM offers a unified and extensible framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access. Furthermore, it enhances understanding by supporting automatic visualization of the underlying mechanisms of these algorithms. For evaluation, MarkLLM offers a comprehensive suite of 12 tools spanning three perspectives, along with two types of automated evaluation pipelines. Through MarkLLM, we aim to support researchers while improving the comprehension and involvement of the general public in LLM watermarking technology, fostering consensus and driving further advancements in research and application. Our code is available at https://github.com/THU-BPM/MarkLLM. |
| title | MarkLLM: An Open-Source Toolkit for LLM Watermarking |
| topic | Cryptography and Security Computation and Language 68T50 I.2.7 |
| url | https://arxiv.org/abs/2405.10051 |