{"total":73,"rows":[{"id":"2504.14225","title":"Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale","created":"2025-04-19","cited_by_count":178,"area":null},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"area":"alignment"},{"id":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81,"area":null},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60,"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":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"area":null},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34,"area":"lr"},{"id":"2410.05613","title":"Stereotype or Personalization? User Identity Biases Chatbot Recommendations","created":"2024-10-08","cited_by_count":34,"area":null},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2502.13012","title":"Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents","created":"2025-02-18","cited_by_count":22,"area":"agents"},{"id":"2507.22168","title":"Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles","created":"2025-07-29","cited_by_count":16,"area":null},{"id":"2502.19312","title":"FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users","created":"2025-02-26","cited_by_count":15,"area":"alignment"},{"id":"2511.07338","title":"DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2602.22680","title":"Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions","created":"2026-02-26","cited_by_count":14,"area":"agents"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2505.17051","title":"Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","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":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"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":"2602.03545","title":"Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2508.20282","title":"Network-Level Prompt and Trait Leakage in Local Research Agents","created":"2025-08-27","cited_by_count":5,"area":"agents"},{"id":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2510.19299","title":"Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties","created":"2025-10-22","cited_by_count":5,"area":"agents"},{"id":"2511.21722","title":"German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2605.20767","title":"The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study","created":"2026-05-20","cited_by_count":5,"area":null},{"id":"2502.13135","title":"Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions","created":"2025-02-18","cited_by_count":4,"area":"agents"},{"id":"2601.15395","title":"Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind","created":"2026-01-21","cited_by_count":4,"area":null},{"id":"2412.16783","title":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2601.20757","title":"Persona Prompting as a Lens on LLM Social Reasoning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2509.11311","title":"Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble","created":"2025-09-14","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","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":"2511.22130","title":"Benchmarking In-context Experiential Learning Through Repeated Product Recommendations","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.11147","title":"MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents","created":"2025-12-11","cited_by_count":1,"area":"agents"},{"id":"2601.02813","title":"HAL: Inducing Human-likeness in LLMs with Alignment","created":"2026-01-06","cited_by_count":1,"area":"alignment"},{"id":"2601.15290","title":"Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios","created":"2025-11-30","cited_by_count":1,"area":"agents"},{"id":"2603.16751","title":"Finding Common Ground in a Sea of Alternatives","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.14539","title":"Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack","created":"2025-06-17","cited_by_count":0,"area":"agents"},{"id":"2509.08022","title":"DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2510.14398","title":"YNTP-100: A Benchmark for Your Next Token Prediction with 100 People","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.05018","title":"Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.06197","title":"Personagram: Bridging Personas and Product Design for Creative Ideation with Multimodal LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.19001","title":"Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.28066","title":"Synonymix: Unified Group Personas for Generative Simulations","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.25895","title":"Three Models of RLHF Annotation: Extension, Evidence, and Authority","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.08274","title":"Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2606.27578","title":"PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"id":"2606.29793","title":"Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.20767","title":"Rushes: A Human Preference Dataset for Pluralistic Alignment","created":"2026-07-22","cited_by_count":0,"area":"alignment"},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.20355","title":"ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.09835","title":"HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.38555","title":"Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.13022","title":"Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development","created":"2026-10-09","cited_by_count":0,"area":null},{"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}