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

Recently, large language models (LLMs) have shown great potential inrecommender systems, either improving existing recommendation models or servingas the backbone. However, there exists a large semantic gap between LLMs andrecommender systems, since items to be recommended are often indexed bydiscrete identifiers (item ID) out of the LLM's vocabulary. In essence, LLMscapture language semantics while recommender systems imply collaborativesemantics, making it difficult to sufficiently leverage the model capacity ofLLMs for recommendation. To address this challenge, in this paper, we propose anew LLM-based recommendation model called LC-Rec, which can better integratelanguage and collaborative semantics for recommender systems. Our approach candirectly generate items from the entire item set for recommendation, withoutrelying on candidate items. Specifically, we make two major contributions inour approach. For item indexing, we design a learning-based vector quantizationmethod with uniform semantic mapping, which can assign meaningful andnon-conflicting IDs (called item indices) for items. For alignment tuning, wepropose a series of specially designed tuning tasks to enhance the integrationof collaborative semantics in LLMs. Our fine-tuning tasks enforce LLMs todeeply integrate language and collaborative semantics (characterized by thelearned item indices), so as to achieve an effective adaptation to recommendersystems. Extensive experiments demonstrate the effectiveness of our method,showing that our approach can outperform a number of competitive baselinesincluding traditional recommenders and existing LLM-based recommenders. Ourcode is available at https://github.com/RUCAIBox/LC-Rec/.

Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation