将注意力推荐与微调大模型结合，提升推荐系统性能。
When Transformers Meet Recommenders: Integrating Self-Attentive Sequential Recommendation with Fine-Tuned LLMs
- 用SASRec捕捉用户行为序列，配合LoRA微调大模型
- 在多个数据集上冷启动和热启动场景均优于基线
- 适合需要融合语义理解与协同过滤的推荐场景
自注意力序列推荐（SASRec）通过注意力机制有效捕捉用户的长期偏好。与此同时，大型语言模型（LLMs）的兴起推动了基于LLM的推荐研究，利用其强大的泛化能力和语言理解能力。然而，仅依赖文本提示时，LLMs往往缺乏领域特定知识和协同信号，影响推荐质量。为此，本文提出SASRecLLM框架，将SASRec作为协同编码器，与使用低秩适应（LoRA）微调的LLM结合，通过映射层对齐两者维度空间，并设计三种针对性训练策略优化混合架构。在多个数据集上的大量实验表明，SASRecLLM在冷启动和热启动场景下均显著优于强基线，表现稳健且一致。该工作推进了基于LLM的推荐研究，提出了一个模块化且高效的融合结构化协同过滤与微调大模型语义能力的范式。代码已开源：https://github.com/kechenkristin/RecLLM
原文摘要 · Abstract (English)
Self-Attentive Sequential Recommendation (SASRec) effectively captures long-term user preferences by applying attention mechanisms to historical interactions. Concurrently, the rise of Large Language Models (LLMs) has motivated research into LLM-based recommendation, which leverages their powerful generalization and language understanding capabilities. However, LLMs often lack the domain-specific knowledge and collaborative signals essential for high-quality recommendations when relying solely on textual prompts. To address this limitation, this study proposes SASRecLLM, a novel framework that integrates SASRec as a collaborative encoder with an LLM fine-tuned using Low-Rank Adaptation (LoRA). The components are connected via a mapping layer to align their dimensional spaces, and three targeted training strategies are designed to optimize the hybrid architecture. Extensive experiments on multiple datasets demonstrate that SASRecLLM achieves robust and consistent improvements over strong baselines in both cold-start and warm-start scenarios. This work advances the field of LLM-based recommendation by presenting a modular and effective paradigm for fusing structured collaborative filtering with the semantic power of fine-tuned LLMs. The implementation is available on GitHub: https://github.com/kechenkristin/RecLLM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。