{"total":22,"rows":[{"id":"2406.09215","title":"On Softmax Direct Preference Optimization for Recommendation","created":"2024-06-13","cited_by_count":64,"area":"alignment"},{"id":"2403.05063","title":"Aligning Large Language Models for Controllable Recommendations","created":"2024-03-08","cited_by_count":19,"area":"alignment"},{"id":"2311.10947","title":"RecExplainer: Aligning Large Language Models for Explaining Recommendation Models","created":"2023-11-18","cited_by_count":14,"area":"alignment"},{"id":"2407.13163","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","created":"2024-07-18","cited_by_count":4,"area":"alignment"},{"id":"2508.18142","title":"Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation","created":"2025-08-25","cited_by_count":4,"area":"alignment"},{"id":"2506.09084","title":"PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models","created":"2025-06-10","cited_by_count":2,"area":"alignment"},{"id":"2507.02255","title":"Listwise Preference Alignment Optimization for Tail Item Recommendation","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2506.02261","title":"What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context","created":"2025-06-02","cited_by_count":1,"area":"alignment"},{"id":"2509.22807","title":"MTRec: Learning to Align with User Preferences via Mental Reward Models","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2601.21452","title":"SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2602.08067","title":"Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations","created":"2026-02-08","cited_by_count":1,"area":"alignment"},{"id":"2605.29141","title":"Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2508.09653","title":"On Negative-aware Preference Optimization for Recommendation","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2509.24189","title":"SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2603.10279","title":"Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF","created":"2026-03-10","cited_by_count":0,"area":"alignment"},{"id":"2603.22335","title":"Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation","created":"2026-03-21","cited_by_count":0,"area":"alignment"},{"id":"2603.29259","title":"Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE","created":"2026-03-31","cited_by_count":0,"area":"alignment"},{"id":"2605.00327","title":"DynamicPO: Dynamic Preference Optimization for Recommendation","created":"2026-05-01","cited_by_count":0,"area":"alignment"},{"id":"2605.16345","title":"Goal-Conditioned Supervised Learning for LLM Fine-Tuning","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2607.20767","title":"Rushes: A Human Preference Dataset for Pluralistic Alignment","created":"2026-07-22","cited_by_count":0,"area":"alignment"},{"id":"2608.06792","title":"Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training","created":"2026-08-07","cited_by_count":0,"area":"alignment"},{"id":"2608.09605","title":"TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation","created":"2026-08-10","cited_by_count":0,"area":"alignment"}],"next_cursor":null}