对比纯大模型与增强型大模型推荐系统，揭示哪种更有效。
Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders
- 将推荐方法分为纯大模型和融合其他技术的增强型两类。
- 构建统一评测平台，在相同条件下比较代表性模型性能。
- 为未来大模型推荐系统研究提供方向与实践参考。
大语言模型（LLMs）通过提供更丰富的语义理解与隐含世界知识，为推荐系统引入了新范式。本研究提出一个系统性分类框架，将现有方法分为两类：(1) 纯大模型推荐系统，仅依赖大模型；(2) 增强型大模型推荐系统，融合非大模型技术以提升性能。该分类框架为审视基于大模型的推荐发展提供了新视角。为实现公平比较，我们构建了一个统一评估平台，在一致实验设置下对代表性模型进行基准测试，揭示影响效果的关键设计选择。最后讨论开放挑战并展望未来研究方向。本工作既提供全面综述，也给出推进下一代大模型驱动推荐系统的实用指导。
原文摘要 · Abstract (English)
Large language models (LLMs) have introduced new paradigms for recommender systems by enabling richer semantic understanding and incorporating implicit world knowledge. In this study, we propose a systematic taxonomy that classifies existing approaches into two categories: (1) Pure LLM Recommenders, which rely solely on LLMs, and (2) Augmented LLM Recommenders, which integrate additional non-LLM techniques to enhance performance. This taxonomy provides a novel lens through which to examine the evolving landscape of LLM-based recommendation. To support fair comparison, we introduce a unified evaluation platform that benchmarks representative models under consistent experimental settings, highlighting key design choices that impact effectiveness. We conclude by discussing open challenges and outlining promising directions for future research. This work offers both a comprehensive overview and practical guidance for advancing next-generation LLM-powered recommender.
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。