{"total":72,"rows":[{"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":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2405.19544","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization","created":"2024-05-29","cited_by_count":24,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","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":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2501.11549","title":"Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas","created":"2025-01-20","cited_by_count":19,"area":"alignment"},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"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":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","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":"2406.16316","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","created":"2024-06-24","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":"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":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","cited_by_count":9,"area":"alignment"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2505.19387","title":"Alignment of large language models with constrained learning","created":"2025-05-26","cited_by_count":8,"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":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","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":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","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":"2509.03672","title":"SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2509.19104","title":"Online Distributionally Robust LLM Alignment via Regression to Relative Reward","created":"2025-09-23","cited_by_count":2,"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":"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":"2606.04284","title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling","created":"2026-06-02","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":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","cited_by_count":1,"area":"alignment"},{"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":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","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":"2605.05003","title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","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":"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":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2604.01312","title":"Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"id":"2604.20685","title":"MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment","created":"2026-04-22","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":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.26397","title":"Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication","created":"2026-05-26","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":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","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":"2608.06400","title":"Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"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":"2608.25200","title":"MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2609.26929","title":"Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment","created":"2026-09-22","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":"2610.00715","title":"Robust Nash Alignment under Preference Uncertainty","created":"2026-09-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}