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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As the capabilities of Large Language Models (LLMs) emerge, they not onlyassist in accomplishing traditional tasks within more efficient paradigms butalso stimulate the evolution of social bots. Researchers have begun exploringthe implementation of LLMs as the driving core of social bots, enabling moreefficient and user-friendly completion of tasks like profile completion, socialbehavior decision-making, and social content generation. However, there iscurrently a lack of systematic research on the behavioral characteristics ofLLMs-driven social bots and their impact on social networks. We have curateddata from Chirper, a Twitter-like social network populated by LLMs-drivensocial bots and embarked on an exploratory study. Our findings indicate that:(1) LLMs-driven social bots possess enhanced individual-level camouflage whileexhibiting certain collective characteristics; (2) these bots have the abilityto exert influence on online communities through toxic behaviors; (3) existingdetection methods are applicable to the activity environment of LLMs-drivensocial bots but may be subject to certain limitations in effectiveness.Moreover, we have organized the data collected in our study into theMasquerade-23 dataset, which we have publicly released, thus addressing thedata void in the subfield of LLMs-driven social bots behavior datasets. Ourresearch outcomes provide primary insights for the research and governance ofLLMs-driven social bots within the research community.

Are you in a Masquerade? Exploring the Behavior and Impact of Large Language Model Driven Social Bots in Online Social Networks