双向知识蒸馏：利用大语言模型增强序列推荐
Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
AI总结：
提出LLMD4Rec双向蒸馏框架，通过动态交互知识交换增强序列推荐，无需额外参数且不增推理成本，显著提升推荐准确性。
摘要：
大语言模型（LLMs）在理解和生成语义模式方面展现了卓越的性能，使其成为序列推荐任务的有力候选者。然而，当与传统推荐模型（CRMs）结合时，LLMs 常常面临高推理成本和静态知识转移方法相关的挑战。在本文中，我们提出了一种新颖的互蒸馏框架 LLMD4Rec，该框架促进了以 LLM 为中心和基于 CRM 的推荐系统之间的动态双向知识交换。与传统的单向蒸馏方法不同，LLMD4Rec 通过交替优化两个模型来实现迭代优化，增强了 CRMs 的语义理解，并丰富了 LLMs 中来自用户-物品交互的协同信号。通过利用样本自适应加权和对齐输出分布，我们的方法无需额外参数即可确保有效的知识转移。在真实世界数据集上的大量实验表明，LLMD4Rec 在多个基准上显著提高了推荐准确性，且不增加推理成本。该方法为在序列推荐系统中结合 LLMs 和 CRMs 的优势提供了一种可扩展且高效的解决方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
