{"total":52,"rows":[{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"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":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","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":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2501.19266","title":"Jackpot! Alignment as a Maximal Lottery","created":"2025-01-31","cited_by_count":17,"area":"alignment"},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"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":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11,"area":null},{"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":"2408.12112","title":"Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards","created":"2024-08-22","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":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2506.12350","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","created":"2025-06-14","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":"2408.10270","title":"SEAL: Systematic Error Analysis for Value ALignment","created":"2024-08-16","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":"2509.04445","title":"Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2510.00263","title":"Judging with Confidence: Calibrating Autoraters to Preference Distributions","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2608.05015","title":"Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2501.06248","title":"Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models","created":"2025-01-08","cited_by_count":2,"area":null},{"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":"2510.20020","title":"Optimized Distortion in Linear Social Choice","created":"2025-10-22","cited_by_count":2,"area":null},{"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":"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":"2601.18824","title":"Differential Voting: Loss Functions For Axiomatically Diverse Aggregation of Heterogeneous Preferences","created":"2026-01-25","cited_by_count":2,"area":"alignment"},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","cited_by_count":2,"area":null},{"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":"2503.10215","title":"Adaptive Preference Aggregation","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","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":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","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":"2603.19510","title":"Linear Social Choice with Few Queries: A Moment-Based Approach","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"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":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"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":"2509.21836","title":"Axiomatic Choice","created":"2025-09-26","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":"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":"2607.02672","title":"Internal Pluralism and the Limits of Pairwise Comparisons","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.22603","title":"Group Preference Collapse in Personalized Multimodal Large Language Models","created":"2026-06-12","cited_by_count":0,"area":"mllm"},{"id":"2607.27255","title":"More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility","created":"2026-07-28","cited_by_count":0,"area":null},{"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":"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":"2609.38287","title":"Social Choice Foundations for Simulation-Augmented Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06892","title":"Axiom Satisfiability of Linear Rewards in Alignment","created":"2026-09-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}