近期研究探索了提高基于大语言模型（LLM）的推荐系统效率和准确性的方法。一种方法侧重于优化训练参数，例如批次大小与负采样，以在内存限制下提高收敛性和推荐质量。另一个研究领域涉及改进大语言模型处理项目信息的方式，通过根据上下文自适应地融合视觉数据，或从项目描述中选择信息量最大的标记以降低计算成本而不牺牲性能。此外，研究人员正在开发模型合并技术以压缩推理痕迹，并初始化项目表示以更好地保留语义信息。
AI
arXiv:2608.10240v1 Announce Type: cross Abstract: Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is u…
arXiv:2608.11061v1 Announce Type: new Abstract: Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, re…
arXiv cs.AI
TIER_1English(EN)·Linh Dieu Le, Tong Chen, Shazia Sadiq, Hongzhi Yin, Ming Jin, Junliang Yu·
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict d…
arXiv cs.AI
TIER_1English(EN)·Changshuai Wei, John Bencina, Phuc Nguyen, Andre Assuncao Silva T Ribeiro, Benjamin Zelditch·
arXiv:2608.10182v1 Announce Type: cross Abstract: Large-scale targeting and recommendation systems are typically built around predictive scores fed into heuristic or local allocation. When the business goal is incremental impact, as in marketing campaigns, incentives, and notific…
arXiv:2608.10929v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the behavioral anchors that align item spaces, such as overlapping user…
Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to material…
Multimodal sequential recommender systems commonly fuse visual and collaborative signals uniformly, treating visual features as generically informative regardless of item or user context. We argue that visual utility, defined as the contribution of visual signals to recommendatio…
Search and recommendation are crucial for understanding user preferences. More and more studies are attempting to jointly model search behavior and recommendation behavior, by integrating user active search and passive recommendation behavior data to better mine user preferences.…
Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often…
Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often…
arXiv:2608.09685v1 Announce Type: new Abstract: Autoregressive semantic ID recommenders are constrained by expensive beam-search decoding, which limits the practical length of item identifiers. Parallel generation methods alleviate this bottleneck by predicting all semantic ID to…
arXiv:2605.20721v2 Announce Type: replace Abstract: Label noise is a central challenge in learning from implicit feedback for recommendation. Conventional approaches discard noisy examples for robustness, but this sacrifices data efficiency. Unlike filtering approaches, Bayes-lab…
arXiv cs.AI
TIER_1English(EN)·Wenqiao Zhu, Chao Xu, Haipang Wu, Ji Liu·
arXiv:2608.09605v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for improving recommendation systems. The effectiveness of LLMs arises from their ability to harness rich textual information and their capacity to model heterogeneous us…
arXiv cs.AI
TIER_1English(EN)·Qingtian Bian, Tieying Li, Marcus de Carvalho, Jiaxing Xu, Hui Fang, Yiping Ke·
arXiv:2608.09580v1 Announce Type: new Abstract: Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user interests across related domains. A key challenge lies in effectively bridging these domains. In single-domain modeling, mode…
arXiv:2608.07816v1 Announce Type: cross Abstract: Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, item…
Large language models (LLMs) are reshaping recommender systems by enabling richer modeling of users, content, and context directly in natural language. At Netflix, we are exploring this direction through GenRec, an LLM-backed recommendation ranker built on top of an in-house foun…
Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential …
Modern recommendation systems on social media platforms such as Meta must model complex social relationships, including friendships, group memberships, and creator interactions, alongside massive and heterogeneous content such as text and video. Traditional recommendation models,…
Large Language Models (LLMs) have emerged as powerful tools for improving recommendation systems. The effectiveness of LLMs arises from their ability to harness rich textual information and their capacity to model heterogeneous user preferences based on users' interaction history…
Recent LLM-based recommenders integrate textual and collaborative signals by projecting collaborative embeddings into the embedding space of the LLM. However, this projection can introduce modality bias that distorts the underlying collaborative structure and limits the usefulnes…
Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, items are often represented through semantic IDs (SIDs…
