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

Large Language Models (LLMs) have demonstrated exceptional capabilities ingeneralizing to new tasks in a zero-shot or few-shot manner. However, theextent to which LLMs can comprehend user preferences based on their previousbehavior remains an emerging and still unclear research question.Traditionally, Collaborative Filtering (CF) has been the most effective methodfor these tasks, predominantly relying on the extensive volume of rating data.In contrast, LLMs typically demand considerably less data while maintaining anexhaustive world knowledge about each item, such as movies or products. In thispaper, we conduct a thorough examination of both CF and LLMs within the classictask of user rating prediction, which involves predicting a user's rating for acandidate item based on their past ratings. We investigate various LLMs indifferent sizes, ranging from 250M to 540B parameters and evaluate theirperformance in zero-shot, few-shot, and fine-tuning scenarios. We conductcomprehensive analysis to compare between LLMs and strong CF methods, and findthat zero-shot LLMs lag behind traditional recommender models that have theaccess to user interaction data, indicating the importance of user interactiondata. However, through fine-tuning, LLMs achieve comparable or even betterperformance with only a small fraction of the training data, demonstratingtheir potential through data efficiency.

Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction