New research tackles recommendation system challenges with semantic factors and explicit feedback
ByPulseAugur Editorial·[49 sources]·
Researchers are developing new methods to improve recommendation systems by addressing limitations in current models. One approach, SaFeAU, enhances collaborative filtering by incorporating semantic factors to better handle sparse data and capture higher-order signals. Another area of focus is leveraging explicit user feedback, such as comments and reviews, to align recommendations with user preferences more accurately and reduce filter bubbles. Additionally, techniques like dataset distillation (FOSTER, Rec-Distill) and embedding control (ACE) are being explored to make large-scale recommendation models more efficient and effective for real-world deployment.
AI
IMPACT
New methods aim to improve recommendation accuracy, efficiency, and user preference alignment, potentially leading to more personalized and explainable systems.
RANK_REASON
The cluster contains multiple academic papers detailing new research methodologies and frameworks for recommender systems.
arXiv:2606.06225v1 Announce Type: cross Abstract: Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no in…
Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no interaction history. In Tubi's production retrieval …
In multi-behavior recommendation, auxiliary behaviors such as clicks, add-to-cart, and purchases can provide richer supervisory information for predicting target behaviors. Although existing graph and hypergraph methods are capable of modeling high-order relationships among users…
Recent LLM-based recommenders enhance language models with collaborative embeddings from user-item interactions, but making such embeddings available does not ensure their proper use during inference. Through a diagnostic attention analysis, we find that the utilization of collab…
arXiv cs.AI
TIER_1English(EN)·Ashmi Banerjee, Adithi Satish, Fitri Nur Aisyah, Wolfgang W\"orndl, Yashar Deldjoo·
arXiv:2508.15030v5 Announce Type: replace Abstract: We propose COLLAB-REC, a multi-agent framework designed to counteract popularity bias and improve diversity in tourism recommendations. In our setup, three LLM-based agents(Personalization, Popularity, and Sustainability) genera…
arXiv:2606.03091v1 Announce Type: cross Abstract: Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces s…
arXiv:2501.02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents a…
arXiv cs.AI
TIER_1English(EN)·Yuecheng Li, Zeyu Song, Jing Yao, Chi Lu, Peng Jiang, Kun Gai·
arXiv:2606.03866v1 Announce Type: cross Abstract: Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID space via post-training (e.g., SFT and RL) remains cha…
arXiv:2606.02883v1 Announce Type: cross Abstract: Recommender systems have grown from content-organization tools into sophisticated systems that shape daily behavior. By controlling what we see, they shape what we perceive, raising concerns about filter bubbles, radicalization, p…
Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID space via post-training (e.g., SFT and RL) remains challenging. Existing LLM4Rec paradigms are bottlenec…
Sequential recommenders weight historical interactions either through positional self-attention as in Transformers or through a single implicit decay schedule as in State-Space Models. Neither makes the multi-scale temporal structure of real user behaviour explicit. We propose MA…
Recent advancements in Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning, reflection, and tool utilization, unlocking new paradigms for automating complex engineering workflows. However, in the domain of sequential recommendation (SR), tuning mod…
arXiv cs.AI
TIER_1English(EN)·Jonathan Mayo, Moshe Unger, Konstantin Bauman·
arXiv:2606.01783v1 Announce Type: cross Abstract: Digital platforms increasingly operate as isolated information silos, limiting their ability to construct comprehensive user representations across domains. Cross-domain recommender systems seek to overcome this limitation by tran…
arXiv:2606.01111v1 Announce Type: new Abstract: Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.g., statistical value) to high-dimensional embeddings (e.g., user-id embeddings, MLP representations) -- to…
arXiv:2508.10312v2 Announce Type: replace Abstract: Recommender systems in concert with Large Language Models (LLMs) present promising avenues for generating semantically-informed recommendations. However, LLM-based recommenders exhibit a tendency to overemphasize semantic correl…
arXiv:2602.07298v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) represent a promising frontier for recommender systems, yet their development has been impeded by the absence of predictable scaling laws, which are crucial for guiding research and optimizing …
arXiv cs.AI
TIER_1English(EN)·Xiangyu Wang, Yawen He, Shivendra Pratap Singh, Han Huang, Mengtong Hu, Sharath Ciddu, Yi-Hsuan Hsieh, Erik Groving, Yi Ding, Jieming Di, Tony Wang, Min Yun, Xiaoyu Chen, Ling Leng, Rob Malkin·
arXiv:2606.00282v1 Announce Type: cross Abstract: Large-scale recommendation systems operate across diverse domains, yet they face the challenges of data sparsity and noisy implicit feedback. Traditional approaches mitigate this via model-specific knowledge distillation from sour…
Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences t…
Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences t…
arXiv cs.IR (Information Retrieval)
TIER_1English(EN)·Duncan J. Watts·
Recommender systems have grown from content-organization tools into sophisticated systems that shape daily behavior. By controlling what we see, they shape what we perceive, raising concerns about filter bubbles, radicalization, polarization, and social inequality. Large language…
Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geomet…
Digital platforms increasingly operate as isolated information silos, limiting their ability to construct comprehensive user representations across domains. Cross-domain recommender systems seek to overcome this limitation by transferring knowledge from a source domain to a targe…
The field of recommender systems (RS) is currently undergoing two profound paradigm shifts. From the perspective of objectives, the goal has shifted beyond mere recommendation accuracy to comprehensive trustworthiness, encompassing multiple dimensions such as robustness, fairness…
Large-scale recommendation systems operate across diverse domains, yet they face the challenges of data sparsity and noisy implicit feedback. Traditional approaches mitigate this via model-specific knowledge distillation from source domains to a target domain. Inspired by the tra…
Collaborative filtering (CF) is widely used in recommender systems (RecSys) due to its simplicity and efficiency. However, existing CF methods follow an instance-level learning paradigm. During the instance learning stage, a large number of uninteracted user-item instances, of wh…
arXiv cs.AI
TIER_1English(EN)·Weizhi Zhang, Wooseong Yang, Yuxin Cui, Zhaohui Guo, Hins Hu, Liangwei Yang, Henry Peng Zou, Qifei Wang, Hanqing Zeng, Jiayi Liu, Yinglong Xia, Philip S. Yu·
arXiv:2605.29141v1 Announce Type: cross Abstract: Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, li…
Text-based sequential recommender systems, while greatly improving recommendation accuracy by incorporating item contexts, are undeniably more expensive to train. By condensing a large dataset into a compact set of synthetic samples for model training, dataset distillation offers…
Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because real-world deployment requires lightweight models with strict serving efficiency and latency guarant…
Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because real-world deployment requires lightweight models with strict serving efficiency and latency guarant…
arXiv:2603.22335v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empi…
arXiv:2605.27450v1 Announce Type: cross Abstract: Modern industrial recommender systems use a deep ranking model to score N candidates against the same user and context features. Standard implementations broadcast context features early in the forward pass, redundantly computing …
Recent advances in the LLM-as-Extractor paradigm leverage large language models (LLMs) to transfer semantically rich item embeddings into sequential recommendation (SR) backbones. However, LLM-generated embeddings often suffer from strong anisotropy. Most vectors are concentrated…
arXiv cs.IR (Information Retrieval)
TIER_1English(EN)·Philip S. Yu·
Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, like comments and reviews. This explicit context fee…
arXiv:2602.11799v2 Announce Type: replace Abstract: Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1)…
arXiv:2602.18907v2 Announce Type: replace Abstract: We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem - existing generative methods rely on surface-level t…
arXiv:2605.16825v2 Announce Type: replace-cross Abstract: Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs…
arXiv:2605.26717v1 Announce Type: cross Abstract: Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing …
Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing approaches typically integrate these signals at ei…
arXiv:2605.25749v1 Announce Type: cross Abstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space…
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end g…
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end g…
arXiv cs.IR (Information Retrieval)
TIER_1English(EN)·Jeremiah D. Deng·
In Semantic-ID (SID) based generative recommendation, each item is represented as a sequence of discrete codes, and an autoregressive model is trained to generate the SID sequence of the next item; top-K performance is then measured by checking whether the SID sequence of the tar…
Modern industrial recommender systems use a deep ranking model to score N candidates against the same user and context features. Standard implementations broadcast context features early in the forward pass, redundantly computing context-only operations N times per request. We pr…
Generative recommendation models can model user behavior as sequences of events and provide a shared backbone for multiple recommendation tasks. In production, however, pre-training gains do not automatically translate into downstream application improvements: task headroom, repe…
Conversational recommender systems aim to provide personalized recommendations via natural language interactions. However, existing approaches either decouple recommendation from dialog generation or rely on retrieval-based pipelines, limiting the integration between recommendati…
Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studies have incorporated multimodal signals to provide richer token-level evidence for generation. Howeve…
Personalized generative recommender systems have emerged as a promising solution for fashion recommendation. However, existing methods primarily rely on implicit visual embeddings from historical interactions, which often contain preference-irrelevant information and result in in…
Sequential recommendation (SR) is traditionally formulated as next-item prediction over a chronological sequence of interacted items. Although recent generative recommendation (GR) methods introduce new machinery, such as semantic IDs, autoregressive decoding, and unified token s…
Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs are still susceptible to the long-standing issue of popul…
