{"total":49,"rows":[{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"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":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2406.15352","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","created":"2024-06-21","cited_by_count":10,"area":"alignment"},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","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":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","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":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","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":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"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":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","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":"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":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2604.10673","title":"Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment","created":"2026-04-12","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":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2503.16480","title":"Human Preferences for Constructive Interactions in Language Model Alignment","created":"2025-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.15527","title":"Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2605.27382","title":"The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs","created":"2026-04-10","cited_by_count":1,"area":"alignment"},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"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":"2510.05465","title":"VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models","created":"2025-10-06","cited_by_count":0,"area":"alignment"},{"id":"2602.05113","title":"Democratic Preference Alignment via Sortition-Weighted RLHF","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.28197","title":"EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling","created":"2026-03-30","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":"2604.27453","title":"From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks","created":"2026-04-30","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":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"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":"2606.29097","title":"TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2606.30116","title":"Open Problems in Constitutional Preference Reconstruction","created":"2026-06-29","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":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.05450","title":"Groupwise Distortion Guarantees for Preference-Based Alignment","created":"2026-10-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}