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

Generating user-friendly explanations regarding why an item is recommendedhas become increasingly common, largely due to advances in language generationtechnology, which can enhance user trust and facilitate more informeddecision-making when using online services. However, existing explainablerecommendation systems focus on using small-size language models. It remainsuncertain what impact replacing the explanation generator with the recentlyemerging large language models (LLMs) would have. Can we expect unprecedentedresults?  In this study, we propose LLMXRec, a simple yet effective two-stageexplainable recommendation framework aimed at further boosting the explanationquality by employing LLMs. Unlike most existing LLM-based recommendation works,a key characteristic of LLMXRec is its emphasis on the close collaborationbetween previous recommender models and LLM-based explanation generators.Specifically, by adopting several key fine-tuning techniques, includingparameter-efficient instructing tuning and personalized prompt techniques,controllable and fluent explanations can be well generated to achieve the goalof explanation recommendation. Most notably, we provide three differentperspectives to evaluate the effectiveness of the explanations. Finally, weconduct extensive experiments over several benchmark recommender models andpublicly available datasets. The experimental results not only yield positiveresults in terms of effectiveness and efficiency but also uncover somepreviously unknown outcomes. To facilitate further explorations in this area,the full code and detailed original results are open-sourced athttps://github.com/GodFire/LLM_rec_explanation/.

Unlocking the Potential of Large Language Models for Explainable Recommendations