{"total":31,"rows":[{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"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":"2203.17118","title":"Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank","created":"2022-03-31","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2402.02171","title":"Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction","created":"2024-02-03","cited_by_count":17,"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":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"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":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2203.02807","title":"Off-Policy Evaluation in Embedded Spaces","created":"2022-03-05","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":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2309.01120","title":"Double Clipping: Less-Biased Variance Reduction in Off-Policy Evaluation","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2408.09168","title":"Ranking Across Different Content Types: The Robust Beauty of Multinomial Blending","created":"2024-08-17","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":"2205.06024","title":"Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling","created":"2022-05-12","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":"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":"2506.20501","title":"Unidentified and Confounded? Understanding Two-Tower Models for Unbiased Learning to Rank","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2603.21485","title":"Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies","created":"2026-03-23","cited_by_count":1,"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":"2502.08993","title":"Off-Policy Evaluation for Recommendations with Missing-Not-At-Random Rewards","created":"2025-02-13","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":"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":"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":"2609.35034","title":"Recommendation Ranking Off-Policy Evaluation under Ranking-Dependent Examination via Examination-Relevance Decomposition","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36740","title":"Efficient Offline Learning of Ranking Policies via Top-$k$ Policy Decomposition","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}