{"total":67,"rows":[{"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":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"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":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"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":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2409.09586","title":"ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs","created":"2024-09-15","cited_by_count":20,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"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":"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":"2403.09704","title":"Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations","created":"2024-03-08","cited_by_count":10,"area":"alignment"},{"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":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"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":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2603.12595","title":"Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback","created":"2026-03-13","cited_by_count":5,"area":"alignment"},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2412.13998","title":"Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes","created":"2024-12-18","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":"2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","created":"2025-11-21","cited_by_count":4,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2509.26601","title":"MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"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":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"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":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"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":"2510.16257","title":"Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback","created":"2025-10-17","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":"2606.13755","title":"Position: Align AI to Our Aspirations, Not Our Flaws","created":"2026-06-11","cited_by_count":1,"area":"alignment"},{"id":"2607.00001","title":"Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2609.12651","title":"Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner","created":"2026-09-11","cited_by_count":1,"area":"alignment"},{"id":"2507.09060","title":"CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment","created":"2025-07-11","cited_by_count":0,"area":"alignment"},{"id":"2602.22146","title":"Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual","created":"2026-02-25","cited_by_count":0,"area":"alignment"},{"id":"2604.25895","title":"Three Models of RLHF Annotation: Extension, Evidence, and Authority","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.10843","title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2605.30323","title":"In-Context Reward Adaptation for Robust Preference Modeling","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2609.17847","title":"Learning Heterogeneous Preferences","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.33803","title":"Diffusion Reward Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.35201","title":"From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.35695","title":"Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}