New research tackles LLM recommender efficiency and accuracy
ByPulseAugur Editorial·[21 sources]·
Recent research explores methods to enhance the efficiency and accuracy of large language model (LLM)-based recommender systems. One approach focuses on optimizing training parameters, such as batch size versus negative sampling, to improve convergence and recommendation quality under memory constraints. Another area of investigation involves improving how LLMs process item information, either by adaptively fusing visual data based on context or by selecting the most informative tokens from item descriptions to reduce computational costs without sacrificing performance. Additionally, researchers are developing techniques for model merging to compress reasoning traces and for initializing item representations to better preserve semantic information.
AI
IMPACT
These advancements aim to make LLM-based recommendation systems more efficient and effective, potentially leading to better user experiences and reduced computational costs.
RANK_REASON
Cluster consists of multiple academic papers on recommendation systems research.
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…
