{"total":74,"rows":[{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74,"area":null},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2405.14758","title":"Axioms for AI Alignment from Human Feedback","created":"2024-05-23","cited_by_count":52,"area":"alignment"},{"id":"2506.09902","title":"PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants","created":"2025-06-11","cited_by_count":48,"area":null},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30,"area":"alignment"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2505.23749","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","created":"2025-05-29","cited_by_count":22,"area":"alignment"},{"id":"2411.13405","title":"On the Way to LLM Personalization: Learning to Remember User Conversations","created":"2024-11-20","cited_by_count":21,"area":null},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","created":"2025-10-18","cited_by_count":18,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2412.16834","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","created":"2024-12-22","cited_by_count":10,"area":"alignment"},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2502.19158","title":"When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning","created":"2025-02-26","cited_by_count":9,"area":"alignment"},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2506.12350","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","created":"2025-06-14","cited_by_count":7,"area":"alignment"},{"id":"2509.24696","title":"T-POP: Test-Time Personalization with Online Preference Feedback","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6,"area":"alignment"},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6,"area":"lr"},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2502.09724","title":"Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning","created":"2025-02-13","cited_by_count":5,"area":"deeprl"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2405.12421","title":"A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback","created":"2024-05-20","cited_by_count":4,"area":"alignment"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2505.21907","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","created":"2025-05-28","cited_by_count":3,"area":"alignment"},{"id":"2511.09002","title":"Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.08786","title":"A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs","created":"2025-12-09","cited_by_count":3,"area":"alignment"},{"id":"2601.04963","title":"Text as a Universal Interface for Transferable Personalization","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2505.20336","title":"MOSLIM:Align with diverse preferences in prompts through reward classification","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2509.23767","title":"From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.23965","title":"The Sign Estimator: LLM Alignment in the Face of Choice Heterogeneity","created":"2025-10-28","cited_by_count":2,"area":"alignment"},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2506.01324","title":"Near-Optimal Clustering in Mixture of Markov Chains","created":"2025-06-02","cited_by_count":1,"area":null},{"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":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2603.20453","title":"Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2604.04261","title":"APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs","created":"2026-04-05","cited_by_count":1,"area":"alignment"},{"id":"2605.06987","title":"Response Time Enhances Alignment with Heterogeneous Preferences","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2505.01706","title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm","created":"2025-05-03","cited_by_count":0,"area":"alignment"},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2601.20760","title":"Exploring Re-inforcement Learning via Human Feedback under User Heterogeneity","created":"2026-01-28","cited_by_count":0,"area":"alignment"},{"id":"2602.04493","title":"PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2602.07218","title":"Collaborative and Efficient Fine-tuning: Leveraging Task Similarity","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.08835","title":"Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.07724","title":"Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.24052","title":"Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.30323","title":"In-Context Reward Adaptation for Robust Preference Modeling","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2605.30903","title":"Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2606.10569","title":"Hidden Consensus:Preference-Validity Compression in Human Feedback","created":"2026-06-09","cited_by_count":0,"area":"alignment"},{"id":"2608.00215","title":"Personalizing Large Language Model Agents with Small Policy Models","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.24046","title":"Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2609.04141","title":"Efficient Test-Time Adaptation through Human-AI Interaction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.02873","title":"ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05450","title":"Groupwise Distortion Guarantees for Preference-Based Alignment","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}