Recommender Systems

Follow this topic Ask about this topic

Recommender systems study how to select and order items—such as videos, products, news, or courses—for each person, helping people find relevant material in large catalogs. Common approaches include collaborative filtering and matrix factorization, sequential and graph neural models, content and multimodal representations, and two-stage retrieval followed by ranking or reranking; bandits and reinforcement learning adapt recommendations from feedback. Recent work also uses language models for conversational, generative, and explainable recommendation, often paired with structured retrieval, semantic item IDs, or offline precomputation to meet serving constraints. Key open tensions are improving cold-start and long-tail discovery while preserving accuracy, latency, privacy, fairness, diversity, and safety, and evaluating gains with realistic temporal tests and online user outcomes rather than ranking metrics alone.

Latest papers

521 papers47 papers in the last four weeks, down 11% on the four weeks before. 0.3% of all new papers.

Apr 9, 2026

Efficient Dataset Selection for Continual Adaptation of Generative Recommenders

Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection can mitigate performance degradation caused by temporal distributional drift while maintaining scalability. We evaluate a range of representation choices and sampling strategies for curating small but informative subsets of user interaction data. Our results demonstrate that gradient-based representations, coupled with distribution-matching, improve downstream model performance, achieving training efficiency gains while preserving robustness to drift. These findings highlight data curation as a practical mechanism for scalable monitoring and adaptive model updates in production-scale recommendation systems.

Cathy Jiao, Juan Elenter, Praveen Ravichandran +7

Carnegie Mellon University · Spotify

Data Selection Recommender Systems Online Continual Learning Generative Recommendation

Apr 8, 2026

NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining

Modern recommendation models have increased to trillions of parameters. As cluster scales expand to O(1k), distributed training bottlenecks shift from computation and memory to data movement, especially lookup and communication latency associated with embeddings. Existing solutions either optimize only one bottleneck or improve throughput by sacrificing training consistency. This paper presents NestPipe, a large-scale decentralized embedding training framework that tackles both bottlenecks while preserving synchronous training semantics. NestPipe exploits two hierarchical sparse parallelism opportunities through nested pipelining. At the inter-batch level, Dual-Buffer Pipelining (DBP) constructs a staleness-free five-stage pipeline through dual-buffer synchronization, mitigating lookup bottlenecks without embedding staleness. At the intra-batch level, we identify the embedding freezing phenomenon, which inspires Frozen-Window Pipelining (FWP) to overlap All2All communication with dense computation via coordinated stream scheduling and key-centric sample clustering. Experiments on production GPU and NPU clusters with 1,536 workers demonstrate that NestPipe achieves up to 3.06x speedup and 94.07% scaling efficiency.

Zhida Jiang, Zhaolong Xing, Huichao Chai +12

Huawei

Distributed Training Pipeline Parallelism Communication-Efficient Distributed Training Recommender Systems

Apr 8, 2026

CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation

Repurchase behavior is a primary signal in large-scale retail recommendation, particularly in categories with frequent replenishment: many items in a user's next basket were previously purchased, and their timing follows stable, item-specific cadences. Yet most next basket repurchase recommendation models represent history as a sequence of discrete basket events indexed by visit order, which cannot explicitly model elapsed calendar time or update item rankings as days pass between purchases. We present CASE (Cadence-Aware Set Encoding) for next basket repurchase recommendation, which decouples item-level cadence learning from cross-item interaction, enabling explicit calendar-time modeling while remaining production-scalable. CASE represents each item's purchase history as a calendar-time signal over a fixed horizon, applies shared multi-scale temporal convolutions to capture recurring rhythms, and uses induced set attention to model cross-item dependencies with sub-quadratic complexity, allowing efficient batch inference at scale. Across three public benchmarks and a proprietary dataset, CASE consistently improves precision, recall, and NDCG at multiple cutoffs compared to strong next basket recommendation baselines. In a production-scale evaluation with tens of millions of users and a large item catalog, CASE achieves up to 8.6% relative precision lift and 9.9% relative recall lift at top-5, showing that scalable cadence-aware modeling yields measurable gains in both benchmark and industrial settings.

Yanan Cao, Ashish Ranjan, Sinduja Subramaniam +3

Walmart Global Tech, Sunnyvale, CA, USA

Recommender Systems Sequential Recommendation

Apr 7, 2026

The Unreasonable Effectiveness of Data for Recommender Systems

In recommender systems, collecting, storing, and processing large-scale interaction data is increasingly costly in terms of time, energy, and computation, yet it remains unclear when additional data stops providing meaningful gains. This paper investigates how offline recommendation performance evolves as the size of the training dataset increases and whether a saturation point can be observed. We implemented a reproducible Python evaluation workflow with two established toolkits, LensKit and RecBole, included 11 large public datasets with at least 7 million interactions, and evaluated 10 tool-algorithm combinations. Using absolute stratified user sampling, we trained models on nine sample sizes from 100,000 to 100,000,000 interactions and measured NDCG@10. Overall, raw NDCG usually increased with sample size, with no observable saturation point. To make result groups comparable, we applied min-max normalization within each group, revealing a clear positive trend in which around 75% of the points at the largest completed sample size also achieved the group's best observed performance. A late-stage slope analysis over the final 10-30% of each group further supported this upward trend: the interquartile range remained entirely non-negative with a median near 1.0. In summary, for traditional recommender systems on typical user-item interaction data, incorporating more training data remains primarily beneficial, while weaker scaling behavior is concentrated in atypical dataset cases and in the algorithmic outlier RecBole BPR under our setup.

Youssef Abdou

Recommender Systems Collaborative Filtering

Apr 7, 2026

LLM Biases

Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While these systems can deliver impressive performance, a key concern is whether they may be less reliable than they appear. We ask a simple but fundamental question: whether the mechanisms that make transformer-based agents effective can also induce systematic biases or distortions? We study this question through a theoretical analysis of transformer-based generative recommenders, in which the next user interaction is generated sequentially from the user history. Focusing on how the model allocates attention across historical evidence, we identify four bias channels: (i) Positional bias: stronger positional encoding shifts influence toward recent history, improving responsiveness but potentially reducing stability and long-term diversity; (ii) Popularity amplification: small frequency differences in data can be magnified into disproportionate exposure, contributing to Matthew effects and echo chambers; (iii) Latent driver bias: when important drivers of user choices are not directly observed, the model can place overly concentrated weight on a small subset of past events, creating overconfident attributions. (iv) Synthetic data bias: when users increasingly follow AI suggestions and platforms retrain on model-shaped synthetic logs, outputs can concentrate over time, and long-tail alternatives can disappear first. Our analysis highlights mechanism-level reliability risks that may not be visible in offline performance metrics. The four bias channels indicate that large-scale deployment may systematically distort exposure and choice. For managers, the immediate implication is to treat these as operational risk factors and to monitor concentration and drift over time, rather than assuming that performance gains alone guarantee reliability.

Jinhui Han, Ming Hu, Xilin Zhang

Guanghua School of Management, Peking University, Beijing 100871, China · Rotman School of Management, University of Toronto, Toronto, Ontario, Canada M5S 3E6

Popularity Bias in Recommender Systems Recommender Systems

Apr 6, 2026

Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation

The growing ubiquity of Extended Reality (XR) is driving Conversational Recommendation Systems (CRS) toward visually immersive experiences. We formalize this paradigm as Immersive CRS (ICRS), where recommended items are highlighted directly in the user's scene-based visual environment and augmented with in-situ labels. While item recommendation has been widely studied, the problem of how to select and evaluate which information to present as immersive labels remains an open problem. To this end, we introduce a principled categorization of information needs into explicit intent satisfaction and proactive information needs and use these to define novel evaluation metrics for item label selection. We benchmark IR-, LLM-, and VLM-based methods across three datasets and ICRS scenarios: fashion, movie recommendation, and retail shopping. Our evaluation reveals three important limitations of existing methods: (1) they fail to leverage scenario-specific information modalities (e.g., visual cues for fashion, meta-data for retail), (2) they present redundant information that is visually inferable, and (3) they poorly anticipate users' proactive information needs from explicit dialogue alone. In summary, this work provides both a novel evaluation paradigm for in-situ item labeling in ICRS and highlights key challenges for future work.

Jiazhou Liang, Yifan Simon Liu, David Guo +3

University of Toronto, Toronto, Canada · University of Waterloo, Waterloo, Canada · 3Vector Institute of Artificial Intelligence, Toronto, Canada

Recommender Systems

Apr 6, 2026

CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation

Generative recommendation (GeneRec) has introduced a new paradigm that represents items as discrete semantic tokens and predicts items in a generative manner. Despite its strong performance across multiple recommendation tasks, existing GeneRec approaches still suffer from severe popularity bias and may even exacerbate it. In this work, we conduct a comprehensive empirical analysis to uncover the root causes of this phenomenon, yielding two core insights: 1) imbalanced tokenization inherits and can further amplify popularity bias from historical item interactions; 2) current training procedures disproportionately favor popular tokens while neglecting semantic relationships among tokens, thereby intensifying popularity bias. Building on these insights, we propose CRAB, a post-hoc debiasing strategy for GeneRec that alleviates popularity bias by mitigating frequency imbalance among semantic tokens. Specifically, given a well-trained model, we first rebalance the codebook by splitting over-popular tokens while preserving their hierarchical semantic structure. Based on the adjusted codebook, we further introduce a tree-structured regularizer to enhance semantic consistency, encouraging more informative representations for unpopular tokens during training. Experiments on real-world datasets demonstrate that CRAB significantly improves recommendation performance by effectively alleviating popularity bias.

Zezhong Fan, Ziheng Chen, Luyi Ma +5

Walmart Global Tech, Sunnyvale, USA · Stony Brook University, NY, USA, Stony Brook, USA

Popularity Bias in Recommender Systems Recommender Systems Generative Recommendation Popularity Bias

Apr 4, 2026

Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation

Sequential Recommendation (SR) learns user preferences from their historical interaction sequences and provides personalized suggestions. In real-world scenarios, most items exhibit sparse interactions, known as the tail-item problem. This issue limits the model's ability to accurately capture item transition patterns. To tackle this, large language models (LLMs) offer a promising solution by capturing semantic relationships between items. Despite previous efforts to leverage LLM-derived embeddings for enriching tail items, they still face the following limitations: 1) They struggle to effectively fuse collaborative signals with semantic knowledge, leading to suboptimal item embedding quality. 2) Existing methods overlook the structural inconsistency between the ID and LLM embedding spaces, causing conflicting signals that degrade recommendation accuracy. In this work, we propose a Fusion and Alignment Enhancement framework with LLMs for Tail-item Sequential Recommendation (FAERec), which improves item representations by generating coherently-fused and structurally consistent embeddings. For the information fusion challenge, we design an adaptive gating mechanism that dynamically fuses ID and LLM embeddings. Then, we propose a dual-level alignment approach to mitigate structural inconsistency. The item-level alignment establishes correspondences between ID and LLM embeddings of the same item through contrastive learning, while the feature-level alignment constrains the correlation patterns between corresponding dimensions across the two embedding spaces. Furthermore, the weights of the two alignments are adjusted by a curriculum learning scheduler to avoid premature optimization of the complex feature-level objective. Extensive experiments across three widely used datasets with multiple representative SR backbones demonstrate the effectiveness and generalizability of our framework.

Zhifu Wei, Yizhou Dang, Guibing Guo +2

Northeastern University, Shenyang, China · Tianjin University, Tianjin, China · Singapore University of Technology and Design, Singapore, Singapore

Recommender Systems Sequential Recommendation Large Language Model-Based Recommendation Latent Space Alignment

Apr 3, 2026

Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation

We introduce Agent4POI, the first POI recommendation framework that generates context-conditioned multimodal representations at recommendation time, rather than relying on static POI embeddings pre-computed independently of context. Existing multimodal systems encode each POI once as a static embedding, a design that precludes reasoning about why the same cafe affords solo work on Monday but group celebration on Friday evening. We formally prove that no pre-computed encoder can satisfy context-sensitive ranking under standard bilinear scoring, motivating inference-time item-side representation. Agent4POI inverts this computation: given a situational context, a four-phase LLM agent generates dynamic, context-specific affordance queries (Phase 1) and executes a five-step cross-modal chain-of-thought over image, review, and metadata evidence (Phase 2). The resulting uncertainty-aware affordance representation is grounded in Gibsonian affordance theory. These cross-modal verdicts form a structured, uncertainty-adjusted affordance representation (Phase 3), which is aligned with user preferences via a semantic caching system for low-latency ranking (Phase 4). On three POI benchmarks and three evaluation configurations (standard, cold-start, context-shift), Agent4POI achieves a 23.2% relative gain over the strongest baseline and degrades by only 7.5% under context-shift versus 16--17% for the strongest baselines. In cold-start scenarios, Agent4POI outperforms the best content-based baseline by up to 2.4x, whereas ID-based methods fail to generalize.

Jinze Wang, Yangchen Zeng, Tiehua Zhang +5

Tongji University · Swinburne University of Technology · Southeast University +4

Recommender Systems Multimodal Recommendation Large Language Model-Based Recommendation

Apr 2, 2026

Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization

Modern recruitment platforms operate under severe information imbalance: job seekers must search over massive, rapidly changing collections of postings, while employers are overwhelmed by high-volume, low-relevance applicant pools. Existing recruitment recommender systems typically rely on keyword matching or single-stage semantic retrieval, which struggle to capture fine-grained alignment between candidate experience and job requirements under real-world scale and cost constraints. We present Synapse, a multi-stage semantic recruitment system that separates high-recall candidate generation from high-precision semantic reranking, combining efficient dense retrieval using FAISS with an ensemble of contrastive learning and Large Language Model (LLM) reasoning. To improve transparency, Synapse incorporates a retrieval-augmented explanation layer that grounds recommendations in explicit evidence. Beyond retrieval, we introduce a novel evolutionary resume optimization framework that treats resume refinement as a black-box optimization problem. Using Differential Evolution with LLM-guided mutation operators, the system iteratively modifies candidate representations to improve alignment with screening objectives, without any labeled data. Evaluation shows that the proposed ensemble improves nDCG@10 by 22% over embedding-only retrieval baselines, while the evolutionary optimization loop consistently yields monotonic improvements in recommender scores, exceeding 60% relative gain across evaluated profiles. We plan to release code and data upon publication.

Ansel Kaplan Erol, Seohee Yoon, Keenan Hom +1

Georgia Institute of Technology, Atlanta, GA, USA

Job-Candidate Matching Recommender Systems Large Language Model-Based Recommendation Large Language Model-Guided Optimization Explainable Recommendation

Apr 2, 2026

Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty

Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms that promote novelty and diversity. In practice, the strength of such interventions is typically controlled using global hyperparameters, fixed regularization weights, heuristic caps, or offline tuning strategies. These approaches implicitly assume that a single level of exploration is appropriate across users, contexts, and stages of interaction. In this work, we study exploration saturation as a user-dependent phenomenon arising from fairness- and novelty-driven recommendation strategies. We define exploration saturation as the point at which further increases in exploration no longer improve user utility and may instead reduce engagement or perceived relevance. Rather than proposing a new fairness-aware algorithm or optimizing a specific objective, we empirically analyze how increasing exploration affects users across varied recommendation models. Through longitudinal experiments using MovieLens-1M and Last.fm datasets, our results indicate that fairness-induced exploration exhibits diminishing or non-monotonic returns and varies substantially across users. In particular, users with limited interaction histories tend to reach saturation earlier, suggesting that uniform fairness or novelty pressure can disproportionately disadvantage certain users. These findings reveal a trade-off between fairness and user experience, suggesting that recommendation systems should adapt not only to relevance but also to the amount of fairness-driven exploration applied to individual users.

Enock O. Ayiku, Evelyn Osei, Emebo Onyeka

University of Massachusetts Boston, Boston, MA, USA · Kansas State University, Manhattan, KS, USA · Virginia Tech, Blacksburg, VA, USA

Recommender Systems Fairness in Recommender Systems Exploration-Exploitation Tradeoff Algorithmic Fairness

Apr 2, 2026

Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges

Video recommender systems are among the most popular and impactful applications of AI, shaping content consumption and influencing culture for billions of users. Traditional single-model recommenders, which optimize static engagement metrics, are increasingly limited in addressing the dynamic requirements of modern platforms. In response, multi-agent architectures are redefining how video recommender systems serve, learn, and adapt to both users and datasets. These agent-based systems coordinate specialized agents responsible for video understanding, reasoning, memory, and feedback, to provide precise, explainable recommendations. In this survey, we trace the evolution of multi-agent video recommendation systems (MAVRS). We combine ideas from multi-agent recommender systems, foundation models, and conversational AI, culminating in the emerging field of large language model (LLM)-powered MAVRS. We present a taxonomy of collaborative patterns and analyze coordination mechanisms across diverse video domains, ranging from short-form clips to educational platforms. We discuss representative frameworks, including early multi-agent reinforcement learning (MARL) systems such as MMRF and recent LLM-driven architectures like MACRec and Agent4Rec, to illustrate these patterns. We also outline open challenges in scalability, multimodal understanding, incentive alignment, and identify research directions such as hybrid reinforcement learning-LLM systems, lifelong personalization and self-improving recommender systems.

Srivaths Ranganathan, Abhishek Dharmaratnakar, Anushree Sinha +1

Google LLC, Mountain View, USA · Google LLC, San Bruno, USA

Recommender Systems Multi-Agent Collaboration Large Language Model-Based Recommendation

Apr 2, 2026

Towards Position-Robust Talent Recommendation via Large Language Models

Talent recruitment is a critical, yet costly process for many industries, with high recruitment costs and long hiring cycles. Existing talent recommendation systems increasingly adopt large language models (LLMs) due to their remarkable language understanding capabilities. However, most prior approaches follow a pointwise paradigm, which requires LLMs to repeatedly process some text and fails to capture the relationships among candidates in the list, resulting in higher token consumption and suboptimal recommendations. Besides, LLMs exhibit position bias and the lost-in-the-middle issue when answering multiple-choice questions and processing multiple long documents. To address these issues, we introduce an implicit strategy to utilize LLM's potential output for the recommendation task and propose L3TR, a novel framework for listwise talent recommendation with LLMs. In this framework, we propose a block attention mechanism and a local positional encoding method to enhance inter-document processing and mitigate the position bias and concurrent token bias issue. We also introduce an ID sampling method for resolving the inconsistency between candidate set sizes in the training phase and the inference phase. We design evaluation methods to detect position bias and token bias and training-free debiasing methods. Extensive experiments on two real-world datasets validated the effectiveness of L3TR, showing consistent improvements over existing baselines.

Silin Du, Hongyan Liu

Department of Management Science and Engineering, Tsinghua University, Beijing, China.

Recommender Systems Large Language Model-Based Recommendation Position Bias

Apr 2, 2026

TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning

Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient alternative to full retraining, yet current MRS unlearning applies reverse updates largely uniformly across model components. We show that this uniform treatment is misaligned with modern MRS: deleted-data influence is distributed unevenly across ranking behavior, modality branches, and model modules. This non-uniformity gives rise to three bottlenecks in MRS unlearning: target-item persistence in the collaborative graph, modality imbalance across feature branches, and concentrated module-level sensitivity in the parameter space. To address this mismatch, we propose targeted reverse update (TRU), a plug-and-play unlearning framework for MRS. Instead of applying a uniform global reversal, TRU performs three coordinated interventions across the model hierarchy: a ranking fusion gate to suppress residual target-item influence in ranking, branch-wise modality scaling to preserve retained multimodal representations, and capacity-aware parameter-group selection to localize reverse updates to deletion-sensitive modules. Across two backbones, three datasets, and three unlearning regimes, TRU achieves a stronger retain--forget trade-off than MMRecUn in most settings. In two challenging user-level cases, TRU also attains favorable operating points among all evaluated baselines. Security audits report the lowest MIA BalAcc and a tie for the lowest ASR among approximate methods in both audited settings, while wall-clock trajectories show earlier convergence to favorable retain--forget regions.

Zhanting Zhou, KaHou Tam, Zeyu Ma +2

University of Electronic Science and Technology of China Chengdu, China · University of Macau Macau, Macao

Recommender Systems Multimodal Recommendation Machine Unlearning

Apr 2, 2026

Scale over Preference: The Impact of AI-Generated Content on Online Content Ecology

The rapid proliferation of Artificial Intelligence-Generated Content (AIGC) is fundamentally restructuring online content ecologies, necessitating a rigorous examination of its behavioral and distributional implications. Leveraging a comprehensive longitudinal dataset comprising tens of millions of users from a leading Chinese video-sharing platform, this study elucidated the distinct creation and consumption behaviors characterizing AIGC versus Human-Generated Content (HGC). We identified a prevalent scale-over-preference dynamic, wherein AIGC creators achieve aggregate engagement comparable to HGC creators through high-volume production, despite a marked consumer preference for HGC. Deeper analysis uncovered the ability of the algorithmic content distribution mechanism in moderating these competing interests regarding AIGC. These findings advocated for the implementation of AIGC-sensitive distribution algorithms and precise governance frameworks to ensure the long-term health of the online content platforms.

Tianhao Shi, Yang Zhang, Xiaoyan Zhao +8

University of Science and Technology of China, Hefei, China. · National University of Singapore, Singapore. · Kuaishou Technology, Beijing, China. +1

Social Media Analysis AI Governance Recommender Systems

Apr 1, 2026

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differences in both design philosophy and architectural structure. In this paper, we propose a unified scaling architecture for recommendation systems, namely UniMixer, to improve scaling efficiency and establish a unified theoretical framework that unifies the mainstream scaling blocks. By transforming the rule-based TokenMixer to an equivalent parameterized structure, we construct a generalized parameterized feature mixing module that allows the token mixing patterns to be optimized and learned during model training. Meanwhile, the generalized parameterized token mixing removes the constraint in TokenMixer that requires the number of heads to be equal to the number of tokens. Furthermore, we establish a unified scaling module design framework for recommender systems, which bridges the connections among attention-based, TokenMixer-based, and factorization-machine-based methods. To further boost scaling ROI, a lightweight UniMixing module is designed, UniMixing-Lite, which further compresses the model parameters and computational cost while significantly improve the model performance. The scaling curves are shown in the following figure. Extensive offline and online experiments are conducted to verify the superior scaling abilities of UniMixer.

Mingming Ha, Guanchen Wang, Linxun Chen +9

Kuaishou Technology, Beijing, China

Recommender Systems Feature Interaction Modeling

Mar 31, 2026

Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE

Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, existing work rarely examines how Direct Preference Optimization (DPO) behaves under implicit feedback, where unobserved items are not reliable negatives. We conduct systematic experiments on multimodal sequential recommendation to compare common negative-selection strategies and their interaction with DPO training. Our central finding is that a simple modification, replacing deterministic hard negatives with stochastic sampling from a dynamic top-K candidate pool, consistently improves ranking performance. We attribute its effectiveness to two factors: (1) reducing erroneous suppressive gradients caused by false negatives, and (2) retaining informative hard signals while smoothing optimization via controlled stochasticity. With an optional sparse Mixture-of-Experts encoder for efficient capacity scaling, RoDPO achieves up to 5.25% NDCG@5 on three Amazon benchmarks, with nearly unchanged inference cost.

Hejin Huang, Jusheng Zhang, Kaitong Cai +2

Sun Yat-sen University · Snap Inc

Recommender Systems Direct Preference Optimization Multimodal Recommendation

Mar 30, 2026

With a Little Help From My Friends: Collective Manipulation in Risk-Controlling Recommender Systems

Recommendation systems have become central gatekeepers of online information, shaping user behaviour across a wide range of activities. In response, users increasingly organize and coordinate to steer algorithmic outcomes toward diverse goals, such as promoting relevant content or limiting harmful material, relying on platform affordances -- such as likes, reviews, or ratings. While these mechanisms can serve beneficial purposes, they can also be leveraged for adversarial manipulation, particularly in systems where such feedback directly informs safety guarantees. In this paper, we study this vulnerability in recently proposed risk-controlling recommender systems, which use binary user feedback (e.g., "Not Interested") to provably limit exposure to unwanted content via conformal risk control. We empirically demonstrate that their reliance on aggregate feedback signals makes them inherently susceptible to coordinated adversarial user behaviour. Using data from a large-scale online video-sharing platform, we show that a small coordinated group (comprising only 1% of the user population) can induce up to a 20% degradation in nDCG for non-adversarial users by exploiting the affordances provided by risk-controlling recommender systems. We evaluate simple, realistic attack strategies that require little to no knowledge of the underlying recommendation algorithm and find that, while coordinated users can significantly harm overall recommendation quality, they cannot selectively suppress specific content groups through reporting alone. Finally, we propose a mitigation strategy that shifts guarantees from the group level to the user level, showing empirically how it can reduce the impact of adversarial coordinated behaviour while ensuring personalized safety for individuals.

Giovanni De Toni, Cristian Consonni, Erasmo Purificato +2

Fondazione Bruno Kessler, Italy · European Commission, Joint Research Centre (JRC)

Recommender Systems Adversarial Attacks Conformal Risk Control

Mar 30, 2026

From Passive Feeds to Guided Discovery: AI-Initiated Interaction for Vague Intent in Content Exploration

Recommendation feeds work well when people are simply browsing, and search works well when they can formulate a query. Between these two cases is a common but poorly supported state: users feel that their feed has become repetitive, yet cannot clearly specify what they want instead. We refer to this state as vague intent. We present Red-Rec, an AI-supported exploration interface for this middle ground. After a period of browsing, the system summarizes patterns in the current feed (e.g., dominant content categories and possible latent interests), offers clickable exploration options, asks at most one follow-up question, and then gradually blends new content into the feed. The design is motivated by a formative study which found that users often recognize feed staleness but struggle to articulate alternatives, suggesting the need for proactive and low-effort interaction.We evaluated Red-Rec in a mixed-design lab study against three comparison conditions: a passive feed, search, and a user-initiated chat interface. Compared with user-initiated chat, Red-Rec led to broader exploration, higher serendipity ratings, and lower interaction effort. Participants in the AI-initiated condition typed very little , relying mainly on option selection, whereas participants in the user-initiated chat condition typed substantially more . We discuss how proactive, option-based AI support can help users move beyond repetitive feeds without undermining their sense of control, and we outline design implications for recommendation interfaces that support open-ended exploration.

Yu Xie, Ying Qi

Human-AI Interaction Recommender Systems

Mar 29, 2026

Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange

Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.

Yin Cheng, Liao Zhou, Xiyu Liang +7

Shopee

Recommender Systems Learning to Rank Large Language Model-Guided Optimization

Mar 29, 2026

Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization

Continual web personalization is essential for engagement, yet real-world non-stationarity and privacy constraints make it hard to adapt quickly without forgetting long-term preferences. We target this gap by seeking a privacy-conscious, parameter-efficient interface that controls stability-plasticity at the user/session level while tying user memory to a shared semantic prior. We propose ProtoFed-SP, a prompt-based framework that injects dual-timescale soft prompts into a frozen backbone: a fast, sparse short-term prompt tracks session intent, while a slow long-term prompt is anchored to a small server-side prototype library that is continually refreshed via differentially private federated aggregation. Queries are routed to Top-M prototypes to compose a personalized prompt. Across eight benchmarks, ProtoFed-SP improves NDCG@10 by +2.9% and HR@10 by +2.0% over the strongest baselines, with notable gains on Amazon-Books (+5.0% NDCG vs. INFER), H&M (+2.5% vs. Dual-LoRA), and Taobao (+2.2% vs. FedRAP). It also lowers forgetting (AF) and Steps-to-95% and preserves accuracy under practical DP budgets. Our contribution is a unifying, privacy-aware prompting interface with prototype anchoring that delivers robust continual personalization and offers a transparent, controllable mechanism to balance stability and plasticity in deployment.

Canran Xiao, Liwei Hou

Shenzhen Campus of Sun Yat-sen University Shenzhen, Guangdong, China · Hunan University Changsha, Hunan, China

Recommender Systems User Preference Modeling Prompt Tuning Federated Continual Learning Prototype-Based Learning

Mar 26, 2026

Visual or Textual: Effects of Explanation Format and Personal Characteristics on the Perception of Explanations in an Educational Recommender System

Explanations are central to improving transparency, trust, and user satisfaction in recommender systems (RS), yet it remains unclear how different explanation formats (visual vs. textual) are suited to users with different personal characteristics (PCs). To this end, we report a within-subject user study (n=54) comparing visual and textual explanations and examine how explanation format and PCs jointly influence perceived control, transparency, trust, and satisfaction in an educational recommender system (ERS). Using robust mixed-effects models, we analyze the moderating effects of a wide range of PCs, including Big Five traits, need for cognition, decision making style, visualization familiarity, and technical expertise. Our results show that a well-designed visual, simple, interactive, selective, easy to understand visualization that clearly and intuitively communicates how user preferences are linked to recommendations, fosters perceived control, transparency, appropriate trust, and satisfaction in the ERS for most users, independent of their PCs. Moreover, we derive a set of guidelines to support the effective design of explanations in ERSs.

Qurat Ul Ain, Mohamed Amine Chatti, Nasim Yazdian Varjani +2

University of Duisburg-Essen Duisburg, Germany · RWTH Aachen University Aachen, Germany

Explainable Recommendation Explanation Evaluation Recommender Systems

Mar 26, 2026

MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation

Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.g., views, clicks, purchases) to enrich preference modeling and alleviate data sparsity issues in traditional single-behavior approaches. However, existing MBR methods face fundamental challenges: they lack principled frameworks to model complex confounding effects from user behavioral habits and item multi-behavior distributions, struggle with effective aggregation of heterogeneous auxiliary behaviors, and fail to align behavioral representations across semantic gaps while accounting for bias distortions. To address these limitations, we propose MCLMR, a novel model-agnostic causal learning framework that can be seamlessly integrated into various MBR architectures. MCLMR first constructs a causal graph to model confounding effects and performs interventions for unbiased preference estimation. Under this causal framework, it employs an Adaptive Aggregation module based on Mixture-of-Experts to dynamically fuse auxiliary behavior information and a Bias-aware Contrastive Learning module to align cross-behavior representations in a bias-aware manner. Extensive experiments on three real-world datasets demonstrate that MCLMR achieves significant performance improvements across various baseline models, validating its effectiveness and generality. All data and code will be made publicly available. For anonymous review, our code is available at the following the link: https://github.com/gitrxh/MCLMR.

Ranxu Zhang, Junjie Meng, Ying Sun +5

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China · Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · RMIT University, Melbourne, Australia +2

Recommender Systems

Mar 26, 2026

Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems

Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and advertiser goals, these platforms frequently maintain an extensive ecosystem of machine learning (ML) models. However, operating at this scale creates significant development and efficiency challenges. Substantial engineering effort is required to regularly refresh ML models and propagate new techniques, which results in long latencies when deploying ML innovations across the ecosystem. We present a large-scale empirical study comparing model performance, efficiency, and ML technique propagation between a standardized model-building approach and independent per-model optimization in recommendation systems. To facilitate this standardization, we propose the Standard Model Template (SMT) -- a framework that generates high-performance models adaptable to diverse data distributions and optimization events. By utilizing standardized, composable ML model components, SMT reduces technique propagation complexity from

O(n \cdot 2^k)

to

O(n + k)

where

n

is the number of models and

k

the number of techniques. Evaluating an extensive suite of models over four global development cycles within Meta's production ads ranking ecosystem, our results demonstrate: (1) a 0.63% average improvement in cross-entropy at neutral serving capacity, (2) a 92% reduction in per-model iteration engineering time, and (3) a

6.3\times

increase in technique-model pair adoption throughput. These findings challenge the conventional wisdom that diverse optimization goals inherently require diversified ML model design.

Jiang Liu, John Martabano Landy, Yao Xuan +14

Meta AI, Menlo Park, California, USA

Recommender Systems CTR Prediction

Mar 25, 2026

Exploring How Fair Model Representations Relate to Fair Recommendations

One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. Models optimized for this definition are typically evaluated on how well demographic attributes can be classified given model representations, with the (implicit) assumption that this measure accurately reflects recommendation parity, i.e., how similar recommendations given to different users are. We challenge this assumption by comparing the amount of demographic information encoded in representations with various measures of how the recommendations differ. We propose two new approaches for measuring how well demographic information can be classified given ranked recommendations. Our results from extensive testing of multiple models on one real and multiple synthetically generated datasets indicate that optimizing for fair representations positively affects recommendation parity, but also that evaluation at the representation level is not a good proxy for measuring this effect when comparing models. We also provide extensive insight into how recommendation-level fairness metrics behave for various models by evaluating their performances on numerous generated datasets with different properties.

Bjørnar Vassøy, Benjamin Kille, Helge Langseth

Norwegian University of Science and Technology, Trondheim, Norway

Fairness in Recommender Systems Algorithmic Fairness Recommender Systems Group Fairness Representation Learning

Mar 25, 2026

LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains

Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "context competition" between past history and current instructions; and (3) Cost-Effective Architecture: relies on tuning-free components and asynchronous batch processing to minimize maintenance costs. Evaluations on public benchmarks (MovieLens-1M, Amazon Prime Pantry) and a sparse industrial dataset (construction risk prediction) demonstrate that LLMAR outperforms state-of-the-art learning-based models (SASRecF), achieving up to a 54.6% nDCG@10 improvement on the industrial dataset. Inference costs remain highly practical (~$1 per 1,000 users). For B2B domains where strict real-time latency is not critical, combining LLM reasoning with self-verification offers a superior alternative to training-based approaches across accuracy, explainability, and operational cost.

Ryogo Hishikawa, Ichiro Kataoka, Shinya Yuda

Hitachi, Ltd. Research and Development Group Hitachi, Ibaraki, Japan · Hitachi Power Solutions Co., Ltd. Hitachi, Ibaraki, Japan

LLM-Assisted Annotation Recommender Systems Large Language Model-Based Recommendation

Mar 24, 2026

Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters

Large Language Models (LLMs) have introduced new capabilities to recommender systems, enabling dynamic, context-aware, and conversational recommendations. However, LLM-based recommender systems inherit and may amplify social biases embedded in their pre-training data, especially when demographic cues are present. Existing fairness solutions either require extra parameters fine-tuning, or suffer from optimization instability. We propose a lightweight and scalable bias mitigation method that combines a kernelized Iterative Null-space Projection (INLP) with a gated Mixture-of-Experts (MoE) adapter. Our approach estimates a closed-form projection that removes single or multiple sensitive attributes from LLM representations with no additional trainable parameters. To preserve task utility, we introduce a two-level MoE adapter that selectively restores useful signals without reintroducing bias. Experiments on two public datasets show that our method reduces attribute leakage across multiple protected variables while maintaining competitive recommendation accuracy.

Nan Cui, Wendy Hui Wang, Yue Ning

Department of Computer Science, Stevens Institute of Technology, Hoboken NJ, USA

Fairness in Recommender Systems Demographic Bias in Language Models Recommender Systems Large Language Model-Based Recommendation

Mar 23, 2026

One Model, Two Markets: Bid-Aware Generative Recommendation

Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence. We introduce control tokens to decouple the decision of whether to show an ad from which item to show. This allows the model to learn valid placement patterns directly from interaction logs, which inherently reflect past successful ad placements. Complementing this, we devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items. We prove that this approach guarantees allocation monotonicity, ensuring that higher bids weakly increase an ad's likelihood of being shown without requiring model retraining. Experiments demonstrate that GEM-Rec allows platforms to dynamically optimize for semantic relevance and platform revenue.

Yanchen Jiang, Zhe Feng, Christopher P. Mah +2

Harvard University · Work done during an internship at Google Research · Google Research

Recommender Systems Generative Recommendation Sequential Recommendation Online Advertising Real-Time Bidding

Mar 23, 2026

PreferRec: Learning and Transferring Pareto Preferences for Multi-objective Re-ranking

Multi-objective re-ranking has become a critical component of modern multi-stage recommender systems, as it tasked to balance multiple conflicting objectives such as accuracy, diversity, and fairness. Existing multi-objective re-ranking methods typically optimize aggregate objectives at the item level using static or handcrafted preference weights. This design overlooks that users inherently exhibit Pareto-optimal preferences at the intent level, reflecting personalized trade-offs among objectives rather than fixed weight combinations. Moreover, most approaches treat re-ranking task for each user as an isolated problem, and repeatedly learn the preferences from scratch. Such a paradigm not only incurs high computational cost, but also ignores the fact that users often share similar preference trade-off structures across objectives. Inspired by the existence of homogeneous multi-objective optimization spaces where Pareto-optimal patterns are transferable, we propose PreferRec, a novel framework that explicitly models and transfers Pareto preferences across users. Specifically, PreferRec is built upon three tightly coupled components: Preference-Aware Pareto Learning aims to capture user intrinsic trade-offs among multiple conflicting objectives at the intent level. By learning Pareto preference representations from re-ranking populations, this component explicitly models how users prioritize different objectives under diverse contexts. Knowledge-Guided Transfer facilitates efficient cross-user knowledge transfer by distilling shared optimization patterns across homogeneous optimization spaces. The transferred knowledge is then used to guide solution selection and personalized re-ranking, biasing the optimization process toward high-quality regions of the Pareto front while preserving user-specific preference characteristics.

Wei Zhou, Wuyang Li, Junkai Ji +5

Shenzhen University, Shenzhen, China · Shenzhen Technology University, Shenzhen, China

Recommender Systems Preference Learning Learning to Rank User Preference Modeling

Mar 23, 2026

MISApp: Multi-Hop Intent-Aware Session Graph Learning for Next App Prediction

Predicting the next mobile app a user will launch is essential for proactive mobile services. Yet accurate prediction remains challenging in real-world settings, where user intent can shift rapidly within short sessions and user-specific historical profiles are often sparse or unavailable, especially under cold-start conditions. Existing approaches mainly model app usage as sequential behavior or local session transitions, limiting their ability to capture higher-order structural dependencies and evolving session intent. To address this issue, we propose MISApp, a profile-free framework for next app prediction based on multi-hop session graph learning. MISApp constructs multi-hop session graphs to capture transition dependencies at different structural ranges, learns session representations through lightweight graph propagation, incorporates temporal context and similarity-based spatial categorization to characterize session conditions, and captures intent evolution from recent interactions. Experiments on two real-world app usage datasets show that MISApp consistently outperforms competitive baselines under both standard and cold-start settings, while maintaining a favorable balance between predictive accuracy and practical efficiency. Further analyses show that multi-hop relations capture higher-hop-specific predictive signals beyond direct 1-Hop adjacency, and that the learned hop-level attention weights align well with structural relevance, providing both empirical and interpretable evidence for the effectiveness of the proposed multi-hop modeling strategy.

Yunchi Yang, Longlong Li, Jianliang Wu +1

School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371, Singapore · School of Mathematics, Shandong University, Jinan 250100, China · Data Science Institute, Shandong University, Jinan 250100, China

Sequential Recommendation Recommender Systems Graph Neural Networks