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

This paper examines the efficacy of utilizing large language models (LLMs) todetect public threats posted online. Amid rising concerns over the spread ofthreatening rhetoric and advance notices of violence, automated contentanalysis techniques may aid in early identification and moderation. Custom datacollection tools were developed to amass post titles from a popular Koreanonline community, comprising 500 non-threat examples and 20 threats. VariousLLMs (GPT-3.5, GPT-4, PaLM) were prompted to classify individual posts aseither "threat" or "safe." Statistical analysis found all models demonstratedstrong accuracy, passing chi-square goodness of fit tests for both threat andnon-threat identification. GPT-4 performed best overall with 97.9% non-threatand 100% threat accuracy. Affordability analysis also showed PaLM API pricingas highly cost-efficient. The findings indicate LLMs can effectively augmenthuman content moderation at scale to help mitigate emerging online risks.However, biases, transparency, and ethical oversight remain vitalconsiderations before real-world implementation.

Efficacy of Utilizing Large Language Models to Detect Public Threat Posted Online