{"total":36,"rows":[{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2410.02504","title":"Dual Active Learning for Reinforcement Learning from Human Feedback","created":"2024-10-03","cited_by_count":20,"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":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"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":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"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":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2601.23096","title":"CATTO: Balancing Preferences and Confidence in Language Models","created":"2026-01-30","cited_by_count":4,"area":"alignment"},{"id":"2603.03336","title":"Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification","created":"2026-02-11","cited_by_count":4,"area":"alignment"},{"id":"2603.17218","title":"Alignment Makes Language Models Normative, Not Descriptive","created":"2026-03-17","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":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2512.00709","title":"When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF","created":"2025-11-30","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":"2503.07806","title":"Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models","created":"2025-03-10","cited_by_count":2,"area":"alignment"},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","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":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"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":"2508.19567","title":"Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning","created":"2025-08-27","cited_by_count":0,"area":"alignment"},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2604.23543","title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","created":"2026-04-26","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":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","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":"2609.35044","title":"BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}