Leveraging Large Language Models for Sequential Recommendation

Jesse Harte, Wouter Zorgdrager, Panos Louridas, Asterios Katsifodimos, Dietmar Jannach, Marios Fragkoulis

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

43 Downloads (Pure)


Sequential recommendation problems have received increasing attention in research during the past few years, leading to the inception of a large variety of algorithmic approaches. In this work, we explore how large language models (LLMs), which are nowadays introducing disruptive effects in many AI-based applications, can be used to build or improve sequential recommendation approaches. Specifically, we devise and evaluate three approaches to leverage the power of LLMs in different ways. Our results from experiments on two datasets show that initializing the state-of-the-art sequential recommendation model BERT4Rec with embeddings obtained from an LLM improves NDCG by 15-20% compared to the vanilla BERT4Rec model. Furthermore, we find that a simple approach that leverages LLM embeddings for producing recommendations, can provide competitive performance by highlighting semantically related items. We publicly share the code and data of our experiments to ensure reproducibility.1

Original languageEnglish
Title of host publicationProceedings of the 17th ACM Conference on Recommender Systems, RecSys 2023
PublisherAssociation for Computing Machinery (ACM)
Number of pages7
ISBN (Electronic)9798400702419
Publication statusPublished - 2023
Event17th ACM Conference on Recommender Systems, RecSys 2023 - Singapore, Singapore
Duration: 18 Sept 202322 Sept 2023

Publication series

NameProceedings of the 17th ACM Conference on Recommender Systems, RecSys 2023


Conference17th ACM Conference on Recommender Systems, RecSys 2023


  • Evaluation
  • Large Language Models
  • Recommender Systems
  • Sequential Recommendation


Dive into the research topics of 'Leveraging Large Language Models for Sequential Recommendation'. Together they form a unique fingerprint.

Cite this