{"total":34,"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":"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":"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":"2108.06889","title":"Causal Incremental Graph Convolution for Recommender System Retraining","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"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":"2102.13302","title":"Variation Control and Evaluation for Generative SlateRecommendations","created":"2021-02-26","cited_by_count":10,"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":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2511.14865","title":"FinTRec: Transformer Based Unified Contextual Ads Targeting and Personalization for Financial Applications","created":"2025-11-18","cited_by_count":4,"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":"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":"2405.09543","title":"Algorithmic Fairness: A Tolerance Perspective","created":"2024-04-26","cited_by_count":2,"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":"2602.18786","title":"CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.20775","title":"Evaluating Uplift Modeling under Structural Biases: Insights into Metric Stability and Model Robustness","created":"2026-03-21","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":"2503.23630","title":"Finding Interest Needle in Popularity Haystack: Improving Retrieval by Modeling Item Exposure","created":"2025-03-31","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":"2507.09566","title":"Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems","created":"2025-07-13","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":"2608.10182","title":"From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation","created":"2026-08-10","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}