{"total":78,"rows":[{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39,"area":null},{"id":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2202.01562","title":"Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","cited_by_count":21,"area":null},{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2304.09085","title":"Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations","created":"2023-04-17","cited_by_count":18,"area":null},{"id":"2306.15098","title":"Off-Policy Evaluation of Ranking Policies under Diverse User Behavior","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2305.02542","title":"Correcting for Interference in Experiments: A Case Study at Douyin","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2405.02141","title":"Multi-Objective Recommendation via Multivariate Policy Learning","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2405.10024","title":"$\\Delta\\text{-}{\\rm OPE}$: Off-Policy Estimation with Pairs of Policies","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2110.12141","title":"Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives","created":"2021-10-23","cited_by_count":8,"area":null},{"id":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","cited_by_count":8,"area":null},{"id":"2307.15893","title":"Online Matching: A Real-time Bandit System for Large-scale Recommendations","created":"2023-07-29","cited_by_count":8,"area":null},{"id":"2109.06723","title":"Simulations in Recommender Systems: An industry perspective","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2205.11788","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2210.07755","title":"Simpson's Paradox in Recommender Fairness: Reconciling differences between per-user and aggregated evaluations","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2304.10900","title":"A Common Misassumption in Online Experiments with Machine Learning Models","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2306.16143","title":"Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2207.12660","title":"Bilateral Self-unbiased Learning from Biased Implicit Feedback","created":"2022-07-26","cited_by_count":3,"area":null},{"id":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2508.00751","title":"Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2101.02553","title":"Off-Policy Evaluation of Slate Policies under Bayes Risk","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2209.08642","title":"Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2302.14139","title":"Scalable End-to-End ML Platforms: from AutoML to Self-serve","created":"2023-02-27","cited_by_count":2,"area":null},{"id":"2303.12973","title":"Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2310.17901","title":"Improving the Knowledge Gradient Algorithm","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2406.18022","title":"Automated Off-Policy Estimator Selection via Supervised Learning","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2506.10677","title":"Exploiting Similarities in A/B Testing with Off-Policy Estimation","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2512.03354","title":"Breaking Determinism: Stochastic Modeling for Reliable Off-Policy Evaluation in Ad Auctions","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2602.14914","title":"Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2109.08621","title":"Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2210.09512","title":"Off-policy evaluation for learning-to-rank via interpolating the item-position model and the position-based model","created":"2022-10-15","cited_by_count":1,"area":null},{"id":"2407.11039","title":"Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation","created":"2024-07-06","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2410.01822","title":"The Importance of Causality in Decision Making: A Perspective on Recommender Systems","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2412.11068","title":"RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2511.04541","title":"Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2603.08370","title":"Unifying On- and Off-Policy Variance Reduction Methods","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2607.01958","title":"A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.26804","title":"Incremental Recommendation via Causal Models","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2105.05733","title":"Thematic recommendations on knowledge graphs using multilayer networks","created":"2021-05-12","cited_by_count":0,"area":null},{"id":"2106.10305","title":"Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2110.12132","title":"Towards the D-Optimal Online Experiment Design for Recommender Selection","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2208.14980","title":"Inverse Propensity Score based offline estimator for deterministic ranking lists using position bias","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2302.02579","title":"Recommender Systems: A Primer","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2309.14046","title":"Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2402.11123","title":"Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2404.08671","title":"Navigating the Evaluation Funnel to Optimize Iteration Speed for Recommender Systems","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2504.08773","title":"Counterfactual Inference under Thompson Sampling","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.00446","title":"Off-Policy Evaluation of Ranking Policies via Embedding-Space User Behavior Modeling","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2507.18756","title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2508.05398","title":"On the Reliability of Sampling Strategies in Offline Recommender Evaluation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.07914","title":"Meta Off-Policy Estimation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.05864","title":"Beyond ATE: Multi-Criteria Design for A/B Testing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2603.07671","title":"Beyond Surrogates: A Quantitative Analysis for Inter-Metric Relationships","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.23022","title":"CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.14604","title":"Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.22012","title":"Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.29600","title":"Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.08725","title":"BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.25408","title":"From Offline Proxies to Online Decisions: A Layered Engagement Evaluation Framework for Conversational AI","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.15696","title":"DRanker: A Transformer-Based Multi-Task Ranking Model for the Disney+ Homepage","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}