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

Nowadays, billions of people engage in communication and express theiropinions on the internet daily. Unfortunately, not all of these expressions arefriendly or compliant, making content moderation an indispensable task. Withthe successful development of Large Language Models (LLMs) in recent years,LLM-based methods have become a feasible solution for handling tasks in variousdomains. However, in the field of content moderation, there is still a lack ofdetailed work that systematically introduces implementation details. In thispaper, we introduce how to fine-tune an LLM model that can be privatelydeployed for content moderation. Specifically, we discuss whether incorporatingreasons during the fine-tuning process would be better or if it should betreated as a classification task directly. We also explore the benefits ofutilizing reasons generated by more powerful LLMs for fine-tuning privatelydeployed models and the impact of different processing approaches when theanswers generated by the more powerful LLMs are incorrect. We report the entireresearch process and the key findings in this paper, hoping to provide valuableexperience for researchers who are fine-tuning privately deployed models intheir domain-specific research.

Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning