English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Potential harms of Large Language Models such as mass misinformation andplagiarism can be partially mitigated if there exists a reliable way to detectmachine generated text. In this paper, we propose a new watermarking method todetect machine-generated texts. Our method embeds a unique pattern within thegenerated text, ensuring that while the content remains coherent and natural tohuman readers, it carries distinct markers that can be identifiedalgorithmically. Specifically, we intervene with the token sampling process ina way which enables us to trace back our token choices during the detectionphase. We show how watermarking affects textual quality and compare ourproposed method with a state-of-the-art watermarking method in terms ofrobustness and detectability. Through extensive experiments, we demonstrate theeffectiveness of our watermarking scheme in distinguishing between watermarkedand non-watermarked text, achieving high detection rates while maintainingtextual quality.

I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text