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

Personalized content-based recommender systems have become indispensabletools for users to navigate through the vast amount of content available onplatforms like daily news websites and book recommendation services. However,existing recommenders face significant challenges in understanding the contentof items. Large language models (LLMs), which possess deep semanticcomprehension and extensive knowledge from pretraining, have proven to beeffective in various natural language processing tasks. In this study, weexplore the potential of leveraging both open- and closed-source LLMs toenhance content-based recommendation. With open-source LLMs, we utilize theirdeep layers as content encoders, enriching the representation of content at theembedding level. For closed-source LLMs, we employ prompting techniques toenrich the training data at the token level. Through comprehensive experiments,we demonstrate the high effectiveness of both types of LLMs and show thesynergistic relationship between them. Notably, we observed a significantrelative improvement of up to 19.32% compared to existing state-of-the-artrecommendation models. These findings highlight the immense potential of bothopen- and closed-source of LLMs in enhancing content-based recommendationsystems. We will make our code and LLM-generated data available for otherresearchers to reproduce our results.

ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models