{"total":100,"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":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31,"area":"alignment"},{"id":"2404.13038","title":"Mapping Social Choice Theory to RLHF","created":"2024-04-19","cited_by_count":27,"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":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2505.18531","title":"Generative RLHF-V: Learning Principles from Multi-modal Human Preference","created":"2025-05-24","cited_by_count":13,"area":"mllm"},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","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":"2505.20627","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching","created":"2025-05-27","cited_by_count":10,"area":"alignment"},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2408.08959","title":"Trust-Oriented Adaptive Guardrails for Large Language Models","created":"2024-08-16","cited_by_count":8,"area":"safety"},{"id":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2503.01894","title":"LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2506.11702","title":"Configurable Preference Tuning with Rubric-Guided Synthetic Data","created":"2025-06-13","cited_by_count":8,"area":"alignment"},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2410.16170","title":"Learning How to Vote with Principles: Axiomatic Insights Into the Collective Decisions of Neural Networks","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2601.10520","title":"Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment","created":"2026-01-15","cited_by_count":5,"area":"lr"},{"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":"2601.11227","title":"Language of Thought Shapes Output Diversity in Large Language Models","created":"2026-01-16","cited_by_count":4,"area":"lr"},{"id":"2602.04990","title":"Position: Machine Learning for Heart Transplant Allocation Policy Optimization Should Account for Incentives","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2408.12927","title":"Abductive and Contrastive Explanations for Scoring Rules in Voting","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2411.00119","title":"Soft Condorcet Optimization for Ranking of General Agents","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2411.10654","title":"Pluralistic Alignment Over Time","created":"2024-11-16","cited_by_count":3,"area":null},{"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":"2510.15839","title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2502.11981","title":"Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2506.03619","title":"Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.04478","title":"Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences","created":"2025-06-04","cited_by_count":2,"area":"lr"},{"id":"2506.17834","title":"Reflective Verbal Reward Design for Pluralistic Alignment","created":"2025-06-21","cited_by_count":2,"area":"alignment"},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.12804","title":"The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation","created":"2025-11-16","cited_by_count":2,"area":"alignment"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.22523","title":"Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents","created":"2026-02-26","cited_by_count":2,"area":"agents"},{"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":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2510.23631","title":"Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2512.21439","title":"Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2602.21556","title":"Power and Limitations of Aggregation in Compound AI Systems","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.16751","title":"Finding Common Ground in a Sea of Alternatives","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2604.17505","title":"Learning Unanimously Acceptable Lotteries via Queries","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2605.12717","title":"The End Justifies the Mean: A Linear Ranking Rule for Proportional Sequential Decisions","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.00291","title":"The Representation-Rationalizability Tradeoff in Reward Learning","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2606.08267","title":"Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics","created":"2026-06-06","cited_by_count":1,"area":null},{"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":"2508.06443","title":"The Fair Game: Auditing & Debiasing AI Algorithms Over Time","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.13960","title":"A Mechanism for Mutual Fairness in Cooperative Games with Replicable Resources -- Extended Version","created":"2025-08-19","cited_by_count":0,"area":"agents"},{"id":"2509.21836","title":"Axiomatic Choice","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.13261","title":"A Ratio-Based Shapley Value for Collaborative Machine Learning - Extended Version","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.13768","title":"Beyond Procedural Compliance: Human Oversight as a Dimension of Well-being Efficacy in AI Governance","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.03003","title":"Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment","created":"2026-02-03","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":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.13294","title":"Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11240","title":"When to Ask a Question: Understanding Communication Strategies in Generative AI Tools","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16291","title":"AI of the People, by the People, for the People: A Social Choice Approach to Collective Control of Artificial Intelligence","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.24052","title":"Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25739","title":"The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.05985","title":"Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.06674","title":"What Do People Actually Want From AI? Mapping Preference Plurality","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.11533","title":"AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.16167","title":"AI Pluralism and the Worlds It Misses","created":"2026-06-15","cited_by_count":0,"area":null},{"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":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00002","title":"Bounded Morality: Defining the Space of Moral Computation","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2607.02672","title":"Internal Pluralism and the Limits of Pairwise Comparisons","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.03910","title":"Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.18631","title":"Preference Reasoning under Indeterminacy in Large Language Models","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"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":"2609.01275","title":"The Constitutional Coverage Trilemma in AI Governance","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05036","title":"Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.07749","title":"Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.22600","title":"From Certain Doom to Survival: Agent-Driven Self-Governance in LLM Agent Societies","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"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":"2609.30555","title":"Proportional Representation in Temporal Voting with Ranked Preferences","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31857","title":"LLM Judge Validation Under Sparse Overlap: From Inference to Design","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38287","title":"Social Choice Foundations for Simulation-Augmented Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39483","title":"Who Owns That? Evaluating Ownership Intuitions in Large Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"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"},{"id":"2610.06892","title":"Axiom Satisfiability of Linear Rewards in Alignment","created":"2026-09-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}