{"total":125,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"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":"2402.05133","title":"Personalized Language Modeling from Personalized Human Feedback","created":"2024-02-06","cited_by_count":132,"area":"alignment"},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123,"area":"alignment"},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123,"area":"alignment"},{"id":"2305.14929","title":"Aligning Language Models to User Opinions","created":"2023-05-24","cited_by_count":99,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73,"area":"alignment"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63,"area":"alignment"},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"area":"alignment"},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31,"area":"alignment"},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"area":"alignment"},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17,"area":"alignment"},{"id":"2410.03145","title":"Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback","created":"2024-10-04","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":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"area":"alignment"},{"id":"2509.01418","title":"On the Alignment of Large Language Models with Global Human Opinion","created":"2025-09-01","cited_by_count":13,"area":"alignment"},{"id":"2406.12074","title":"COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities","created":"2024-06-17","cited_by_count":12,"area":"alignment"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","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":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","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":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2502.00313","title":"Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values","created":"2025-02-01","cited_by_count":9,"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":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","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":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7,"area":"alignment"},{"id":"2505.00038","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","created":"2025-04-29","cited_by_count":7,"area":"alignment"},{"id":"2508.08509","title":"Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression","created":"2025-08-11","cited_by_count":7,"area":"alignment"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2406.05902","title":"Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback","created":"2024-06-09","cited_by_count":6,"area":"alignment"},{"id":"2508.05553","title":"Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs","created":"2025-08-07","cited_by_count":6,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"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":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2509.15090","title":"Emergent Alignment via Competition","created":"2025-09-18","cited_by_count":5,"area":"alignment"},{"id":"2308.06385","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","created":"2023-08-11","cited_by_count":4,"area":"alignment"},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2509.14434","title":"Value Alignment of Social Media Ranking Algorithms","created":"2025-09-17","cited_by_count":4,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","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":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","cited_by_count":3,"area":"alignment"},{"id":"2501.14294","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","created":"2025-01-24","cited_by_count":3,"area":"alignment"},{"id":"2507.16679","title":"PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"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":"2510.13154","title":"The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs","created":"2025-10-15","cited_by_count":3,"area":"alignment"},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","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":"2503.12528","title":"Investigating Human-Aligned Large Language Model Uncertainty","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2508.01930","title":"Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback","created":"2025-08-03","cited_by_count":2,"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":"2509.11311","title":"Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble","created":"2025-09-14","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":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2606.21102","title":"Incoherent Values? Probing LLM Preferences Through Parametric Variation","created":"2026-06-19","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":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2509.00673","title":"Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection","created":"2025-08-31","cited_by_count":1,"area":"alignment"},{"id":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2603.15527","title":"Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2603.20453","title":"Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences","created":"2026-03-20","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":"2604.08757","title":"Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2605.28802","title":"Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2606.09735","title":"The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2606.13755","title":"Position: Align AI to Our Aspirations, Not Our Flaws","created":"2026-06-11","cited_by_count":1,"area":"alignment"},{"id":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2609.25760","title":"The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance","created":"2026-09-22","cited_by_count":1,"area":"alignment"},{"id":"2504.15719","title":"Implementing Rational Choice Functions with LLMs and Measuring their Alignment with User Preferences","created":"2025-04-22","cited_by_count":0,"area":"alignment"},{"id":"2507.12041","title":"Granular feedback merits sophisticated aggregation","created":"2025-07-16","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}