{"total":70,"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":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"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":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124,"area":"alignment"},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"area":"alignment"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"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":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"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":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"area":"alignment"},{"id":"2402.00742","title":"Transforming and Combining Rewards for Aligning Large Language Models","created":"2024-02-01","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2410.16027","title":"ComPO: Community Preferences for Language Model Personalization","created":"2024-10-21","cited_by_count":19,"area":"alignment"},{"id":"2501.11549","title":"Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas","created":"2025-01-20","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":"2402.17358","title":"SoFA: Shielded On-the-fly Alignment via Priority Rule Following","created":"2024-02-27","cited_by_count":18,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"area":"alignment"},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15,"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":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"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":"2406.07295","title":"Multi-objective Reinforcement learning from AI Feedback","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2502.18699","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2406.00024","title":"Embedding-Aligned Language Models","created":"2024-05-24","cited_by_count":9,"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":"2407.17482","title":"Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?","created":"2024-07-02","cited_by_count":8,"area":"alignment"},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2407.14477","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment","created":"2024-07-19","cited_by_count":5,"area":"alignment"},{"id":"2410.14184","title":"MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time","created":"2024-10-18","cited_by_count":5,"area":"alignment"},{"id":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","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":"2410.21533","title":"L3Ms -- Lagrange Large Language Models","created":"2024-10-28","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":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2506.00079","title":"Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values","created":"2025-05-30","cited_by_count":2,"area":"alignment"},{"id":"2506.02479","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","created":"2025-06-03","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":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","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":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2508.07638","title":"Data Selection for LLM Alignment Using Fine-Grained Preferences","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2604.00997","title":"Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization","created":"2026-04-01","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":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","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":"2410.13334","title":"BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models","created":"2024-10-17","cited_by_count":0,"area":"alignment"},{"id":"2507.09060","title":"CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment","created":"2025-07-11","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":"2604.01312","title":"Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"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":"2607.01392","title":"Multi-Objective Exploration and Preference Optimization via Mutual Information","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.20515","title":"Reliability-Aware LLM Alignment from Inconsistent Human Feedback","created":"2026-07-07","cited_by_count":0,"area":"alignment"},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2607.29559","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"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"}],"next_cursor":null}