Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jiongran, Liu, Jiahao, Li, Dongsheng, Zhang, Guangping, Han, Mingzhe, Gu, Hansu, Zhang, Peng, Shang, Li, Lu, Tun, Gu, Ning
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918032185491456
author Wu, Jiongran
Liu, Jiahao
Li, Dongsheng
Zhang, Guangping
Han, Mingzhe
Gu, Hansu
Zhang, Peng
Shang, Li
Lu, Tun
Gu, Ning
author_facet Wu, Jiongran
Liu, Jiahao
Li, Dongsheng
Zhang, Guangping
Han, Mingzhe
Gu, Hansu
Zhang, Peng
Shang, Li
Lu, Tun
Gu, Ning
contents Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommendation tasks. However, when combined with conventional recommendation models (CRMs), LLMs often face challenges related to high inference costs and static knowledge transfer methods. In this paper, we propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange between LLM-centric and CRM-based recommendation systems. Unlike traditional unidirectional distillation methods, LLMD4Rec enables iterative optimization by alternately refining both models, enhancing the semantic understanding of CRMs and enriching LLMs with collaborative signals from user-item interactions. By leveraging sample-wise adaptive weighting and aligning output distributions, our approach eliminates the need for additional parameters while ensuring effective knowledge transfer. Extensive experiments on real-world datasets demonstrate that LLMD4Rec significantly improves recommendation accuracy across multiple benchmarks without increasing inference costs. This method provides a scalable and efficient solution for combining the strengths of both LLMs and CRMs in sequential recommendation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
Wu, Jiongran
Liu, Jiahao
Li, Dongsheng
Zhang, Guangping
Han, Mingzhe
Gu, Hansu
Zhang, Peng
Shang, Li
Lu, Tun
Gu, Ning
Information Retrieval
Artificial Intelligence
Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommendation tasks. However, when combined with conventional recommendation models (CRMs), LLMs often face challenges related to high inference costs and static knowledge transfer methods. In this paper, we propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange between LLM-centric and CRM-based recommendation systems. Unlike traditional unidirectional distillation methods, LLMD4Rec enables iterative optimization by alternately refining both models, enhancing the semantic understanding of CRMs and enriching LLMs with collaborative signals from user-item interactions. By leveraging sample-wise adaptive weighting and aligning output distributions, our approach eliminates the need for additional parameters while ensuring effective knowledge transfer. Extensive experiments on real-world datasets demonstrate that LLMD4Rec significantly improves recommendation accuracy across multiple benchmarks without increasing inference costs. This method provides a scalable and efficient solution for combining the strengths of both LLMs and CRMs in sequential recommendation systems.
title Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2505.18120