一篇新论文探讨了用户状态表示在上下文多臂老虎机（CMAB）推荐系统中的关键作用，发现状态表示的变化比老虎机算法本身的改变能带来更大的性能提升。研究强调，没有一种单一的嵌入或聚合策略是普遍优越的，这强调了领域特定评估的必要性。另一项研究介绍了BEAR，一种用于推荐任务的大型语言模型（LLMs）的新型微调目标，该目标在训练过程中明确考虑了束搜索行为，以解决训练和推理之间的一致性问题。此外，一篇论文提出了一种衡量推荐系统稳定性和可塑性的方法，评估模型如何适应重新训练和数据模式的变化。 AI
影响 推荐系统用户状态表示和大型语言模型微调的进步可能带来更个性化、更有效的用户体验。
排序理由 该集群包含多篇在arXiv上发表的学术论文，重点关注推荐系统和大型语言模型应用的研究。
AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →
arXiv:2502.14541v3 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) has opened new opportunities in recommender systems by enabling zero-shot recommendation without conventional training. Despite their potential, most existing works rely sole…
arXiv:2604.26651v1 Announce Type: cross Abstract: With the increasing availability of online information, recommender systems have become an important tool for many web-based systems. Due to the continuous aspect of recommendation environments, these systems increasingly rely on …
With the increasing availability of online information, recommender systems have become an important tool for many web-based systems. Due to the continuous aspect of recommendation environments, these systems increasingly rely on contextual multi-armed bandits (CMAB) to deliver p…
arXiv:2508.03941v3 Announce Type: replace-cross Abstract: The typical offline protocol to evaluate recommendation algorithms is to collect a dataset of user-item interactions and then use a part of this dataset to train a model, and the remaining data to measure how closely the m…
arXiv:2601.22925v2 Announce Type: replace-cross Abstract: Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utiliz…
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
Breaking it into offline vs. online environments, and candidate retrieval vs. ranking steps.
A whirlwind tour of bandits, embedding+MLP, sequences, graph, and user embeddings.
Why real-time? How have China & US companies built them? How to design & build an MVP?