{"total":132,"rows":[{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2512.06688","title":"PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory","created":"2025-12-07","cited_by_count":88,"area":"agents"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74,"area":"alignment"},{"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":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73,"area":"alignment"},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"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":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2507.09650","title":"Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset","created":"2025-07-13","cited_by_count":35,"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":"2512.06690","title":"Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation","created":"2025-12-07","cited_by_count":30,"area":"lr"},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"id":"2502.20616","title":"PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data","created":"2025-02-28","cited_by_count":27,"area":"rag"},{"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":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2504.05731","title":"Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation","created":"2025-04-08","cited_by_count":24,"area":"rag"},{"id":"2501.06655","title":"Personalized Preference Fine-tuning of Diffusion Models","created":"2025-01-11","cited_by_count":22,"area":"diffusion"},{"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":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2410.16027","title":"ComPO: Community Preferences for Language Model Personalization","created":"2024-10-21","cited_by_count":19,"area":"alignment"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2507.04607","title":"PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process","created":"2025-07-07","cited_by_count":18,"area":"lr"},{"id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","created":"2025-10-18","cited_by_count":18,"area":null},{"id":"2602.16173","title":"Learning Personalized Agents from Human Feedback","created":"2026-02-18","cited_by_count":18,"area":"alignment"},{"id":"2412.11167","title":"Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette","created":"2024-12-15","cited_by_count":16,"area":"agents"},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16,"area":null},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2509.25137","title":"The Era of Real-World Human Interaction: RL from User Conversations","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2510.21903","title":"TOM-SWE: User Mental Modeling For Software Engineering Agents","created":"2025-10-24","cited_by_count":13,"area":"agents"},{"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":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","cited_by_count":11,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2509.21730","title":"ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation","created":"2025-09-26","cited_by_count":11,"area":null},{"id":"2502.15086","title":"Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models","created":"2025-02-20","cited_by_count":10,"area":"safety"},{"id":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2603.04191","title":"Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions","created":"2026-03-04","cited_by_count":10,"area":null},{"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":"2503.18008","title":"Personalized Language Models via Privacy-Preserving Evolutionary Model Merging","created":"2025-03-23","cited_by_count":8,"area":null},{"id":"2506.11702","title":"Configurable Preference Tuning with Rubric-Guided Synthetic Data","created":"2025-06-13","cited_by_count":8,"area":"alignment"},{"id":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","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":"2511.05616","title":"Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization","created":"2025-11-06","cited_by_count":7,"area":"diffusion"},{"id":"2601.20162","title":"Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction","created":"2026-01-28","cited_by_count":7,"area":"agents"},{"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":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2507.15692","title":"Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions","created":"2025-07-21","cited_by_count":6,"area":"mllm"},{"id":"2508.04698","title":"FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data","created":"2025-08-06","cited_by_count":6,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"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":"2409.18203","title":"Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2410.21159","title":"CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants","created":"2024-10-28","cited_by_count":5,"area":"alignment"},{"id":"2508.10028","title":"PREF: Reference-Free Evaluation of Personalised Text Generation in LLMs","created":"2025-08-08","cited_by_count":5,"area":null},{"id":"2511.08590","title":"GMTRouter: Personalized LLM Router over Multi-turn User Interactions","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2601.12078","title":"Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization","created":"2026-01-17","cited_by_count":5,"area":"rag"},{"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":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2505.23827","title":"ValueSim: Generating Backstories to Model Individual Value Systems","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2602.00742","title":"CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs","created":"2026-01-31","cited_by_count":4,"area":null},{"id":"2602.12116","title":"P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2510.11952","title":"GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2603.06595","title":"Rethinking Personalization in Large Language Models at the Token Level","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2405.07838","title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations","created":"2024-05-13","cited_by_count":2,"area":"deeprl"},{"id":"2412.15957","title":"Learning Personalized Prompts for Healthcare Guidance","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2503.08035","title":"Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations","created":"2025-03-11","cited_by_count":2,"area":"alignment"},{"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":"2506.00930","title":"Aligning VLM Assistants with Personalized Situated Cognition","created":"2025-06-01","cited_by_count":2,"area":"mllm"},{"id":"2507.20728","title":"Learning the Value Systems of Societies from Preferences","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2508.14076","title":"PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning","created":"2025-08-12","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":"2510.11194","title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2604.11259","title":"Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2604.13846","title":"Beyond Static Personas: Situational Personality Steering for Large Language Models","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.17657","title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","created":"2026-06-16","cited_by_count":2,"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":"2510.16232","title":"Personalized Collaborative Learning with Affinity-Based Variance Reduction","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2511.05407","title":"Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning","created":"2025-11-07","cited_by_count":1,"area":"alignment"},{"id":"2601.17569","title":"Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations","created":"2026-01-24","cited_by_count":1,"area":"rag"},{"id":"2602.22606","title":"CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2604.00997","title":"Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.27805","title":"ChildEval: When large language models meet children's personalities","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.28073","title":"StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment","created":"2026-05-27","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}