{"total":24,"rows":[{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2412.04628","title":"Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts","created":"2024-12-05","cited_by_count":9,"area":"alignment"},{"id":"2504.15477","title":"In-context Ranking Preference Optimization","created":"2025-04-21","cited_by_count":9,"area":"alignment"},{"id":"2505.16995","title":"DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization","created":"2025-05-22","cited_by_count":5,"area":"alignment"},{"id":"2506.16114","title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","created":"2025-06-19","cited_by_count":3,"area":"alignment"},{"id":"2601.07449","title":"RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking","created":"2026-01-12","cited_by_count":3,"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":"2507.05179","title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations","created":"2025-07-07","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":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2510.23631","title":"Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling","created":"2025-10-24","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":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2603.04946","title":"LocalSUG: City-Preference-Enhanced LLM for Query Suggestion in Local-Life Services","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2605.10784","title":"MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization","created":"2026-05-11","cited_by_count":1,"area":"alignment"},{"id":"2503.10723","title":"RankPO: Preference Optimization for Job-Talent Matching","created":"2025-03-13","cited_by_count":0,"area":"alignment"},{"id":"2508.09653","title":"On Negative-aware Preference Optimization for Recommendation","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2510.13830","title":"Users as Annotators: LLM Preference Learning from Comparison Mode","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2602.19423","title":"Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy","created":"2026-02-23","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":"2604.15602","title":"GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization","created":"2026-04-17","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":"2605.20696","title":"Distributed Direct Preference Optimization","created":"2026-05-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}