2023
DOI: 10.48550/arxiv.2301.10226
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

A Watermark for Large Language Models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
89
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
2
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 44 publications
(89 citation statements)
references
References 0 publications
0
89
0
Order By: Relevance
“…In addition, tools, such as the recently released GPTZero [63], which uses perplexity, as a measure that hints at generalization capabilities (of the agent by which the text was written), to detect AI involvement in text writing, are expected to provide additional support. More advanced techniques aim at watermarking the content generated by language models [64,65], e.g., by biasing the content generation towards terms, which are rather unlikely to be jointly used by humans in a text passage. In the long run, however, we believe that developing curricula and instructions that encourage the creative and evidence-based use of large language models will be the key to solving this problem.…”
Section: • Incorporating Human Expertise and Teachers To Review Valid...mentioning
confidence: 99%
“…In addition, tools, such as the recently released GPTZero [63], which uses perplexity, as a measure that hints at generalization capabilities (of the agent by which the text was written), to detect AI involvement in text writing, are expected to provide additional support. More advanced techniques aim at watermarking the content generated by language models [64,65], e.g., by biasing the content generation towards terms, which are rather unlikely to be jointly used by humans in a text passage. In the long run, however, we believe that developing curricula and instructions that encourage the creative and evidence-based use of large language models will be the key to solving this problem.…”
Section: • Incorporating Human Expertise and Teachers To Review Valid...mentioning
confidence: 99%
“…Since these approaches rely on a neural network for their detection, they can be vulnerable to adversarial and poisoning attacks [Goodfellow et al, 2014, Sadasivan et al, 2023, Kumar et al, 2022. Another line of work aims to watermark AI-generated texts to ease their detection [Atallah et al, 2001, Wilson et al, 2014, Kirchenbauer et al, 2023, Zhao et al, 2023. Watermarking eases the detection of LLM output text by imprinting specific patterns on them.…”
Section: Introductionmentioning
confidence: 99%
“…Watermarking eases the detection of LLM output text by imprinting specific patterns on them. Soft watermarking proposed in Kirchenbauer et al [2023] partitions tokens into green and red lists to help create these patterns. A watermarked LLM samples a token, with high probability, from the green list determined by its prefix token.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations