{"total":63,"rows":[{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34,"area":"lr"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2501.12735","title":"Online Preference Alignment for Language Models via Count-based Exploration","created":"2025-01-22","cited_by_count":26,"area":"alignment"},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"area":"lr"},{"id":"2502.04270","title":"PILAF: Optimal Human Preference Sampling for Reward Modeling","created":"2025-02-06","cited_by_count":20,"area":"alignment"},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","cited_by_count":13,"area":"alignment"},{"id":"2510.08696","title":"Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2412.16834","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","created":"2024-12-22","cited_by_count":10,"area":"alignment"},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","cited_by_count":9,"area":"alignment"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2510.16614","title":"Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards","created":"2025-10-18","cited_by_count":9,"area":"lr"},{"id":"2406.06887","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","created":"2024-06-11","cited_by_count":8,"area":"alignment"},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2505.20268","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2412.10616","title":"Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration","created":"2024-12-13","cited_by_count":6,"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":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2503.22137","title":"Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF","created":"2025-03-28","cited_by_count":5,"area":"alignment"},{"id":"2505.20556","title":"Learning a Pessimistic Reward Model in RLHF","created":"2025-05-26","cited_by_count":5,"area":"alignment"},{"id":"2502.14560","title":"Less is More: Improving LLM Alignment via Preference Data Selection","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2505.21907","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","created":"2025-05-28","cited_by_count":3,"area":"alignment"},{"id":"2506.01523","title":"Beyond RLHF: A Unified Theoretical Framework of Alignment","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2506.06292","title":"Mutual-Taught for Co-adapting Policy and Reward Models","created":"2025-05-17","cited_by_count":3,"area":"alignment"},{"id":"2509.23371","title":"Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization","created":"2025-09-27","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":"2602.15012","title":"Cold-Start Personalization via Training-Free Priors from Structured World Models","created":"2026-02-16","cited_by_count":3,"area":"wm"},{"id":"2602.20696","title":"PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding","created":"2026-02-24","cited_by_count":3,"area":null},{"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":"2510.03269","title":"General Exploratory Bonus for Optimistic Exploration in RLHF","created":"2025-09-27","cited_by_count":2,"area":"alignment"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2409.17534","title":"Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization","created":"2024-09-26","cited_by_count":1,"area":"alignment"},{"id":"2508.10530","title":"Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?","created":"2025-08-14","cited_by_count":1,"area":"alignment"},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2602.20457","title":"Oracle-Robust Online Alignment for Large Language Models","created":"2026-02-24","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":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","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":"2506.08643","title":"MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.22633","title":"Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback","created":"2025-09-26","cited_by_count":0,"area":"alignment"},{"id":"2511.12867","title":"Bootstrapping LLMs via Preference-Based Policy Optimization","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2602.01581","title":"Nearly Optimal Active Preference Learning and Its Application to LLM Alignment","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2605.04477","title":"Data-dependent Exploration for Online Reinforcement Learning from Human Feedback","created":"2026-05-06","cited_by_count":0,"area":"alignment"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.16712","title":"Recall Isn't Enough: Bounding Commitments in Personalized Language Systems","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}