Improve Temporal Awareness of LLMs for Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chu, Zhendong, Wang, Zichao, Zhang, Ruiyi, Ji, Yangfeng, Wang, Hongning, Sun, Tong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911866892058624
author Chu, Zhendong
Wang, Zichao
Zhang, Ruiyi
Ji, Yangfeng
Wang, Hongning
Sun, Tong
author_facet Chu, Zhendong
Wang, Zichao
Zhang, Ruiyi
Ji, Yangfeng
Wang, Hongning
Sun, Tong
contents Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data, such as sequential recommendation. In this paper, we aim to improve temporal awareness of LLMs by designing a principled prompting framework inspired by human cognitive processes. Specifically, we propose three prompting strategies to exploit temporal information within historical interactions for LLM-based sequential recommendation. Besides, we emulate divergent thinking by aggregating LLM ranking results derived from these strategies. Evaluations on MovieLens-1M and Amazon Review datasets indicate that our proposed method significantly enhances the zero-shot capabilities of LLMs in sequential recommendation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02778
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improve Temporal Awareness of LLMs for Sequential Recommendation
Chu, Zhendong
Wang, Zichao
Zhang, Ruiyi
Ji, Yangfeng
Wang, Hongning
Sun, Tong
Information Retrieval
Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data, such as sequential recommendation. In this paper, we aim to improve temporal awareness of LLMs by designing a principled prompting framework inspired by human cognitive processes. Specifically, we propose three prompting strategies to exploit temporal information within historical interactions for LLM-based sequential recommendation. Besides, we emulate divergent thinking by aggregating LLM ranking results derived from these strategies. Evaluations on MovieLens-1M and Amazon Review datasets indicate that our proposed method significantly enhances the zero-shot capabilities of LLMs in sequential recommendation tasks.
title Improve Temporal Awareness of LLMs for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2405.02778