{"total":123,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"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":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74,"area":"alignment"},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66,"area":null},{"id":"2404.11972","title":"Aligning Language Models to Explicitly Handle Ambiguity","created":"2024-04-18","cited_by_count":56,"area":"agents"},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2405.19544","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization","created":"2024-05-29","cited_by_count":24,"area":"alignment"},{"id":"2508.21184","title":"BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design","created":"2025-08-28","cited_by_count":24,"area":null},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","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":"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":"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":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","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":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"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":"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":"2505.17051","title":"Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2405.06909","title":"Fairness in Reinforcement Learning: A Survey","created":"2024-05-11","cited_by_count":9,"area":"deeprl"},{"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":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","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":"2505.19387","title":"Alignment of large language models with constrained learning","created":"2025-05-26","cited_by_count":8,"area":"alignment"},{"id":"2605.08956","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2502.09724","title":"Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning","created":"2025-02-13","cited_by_count":5,"area":"deeprl"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2510.15975","title":"Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity","created":"2025-10-13","cited_by_count":5,"area":"safety"},{"id":"2510.21977","title":"Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributions","created":"2025-10-24","cited_by_count":5,"area":null},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2503.04734","title":"What can large language models do for sustainable food?","created":"2025-02-02","cited_by_count":4,"area":null},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","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":"2603.23301","title":"Steering LLMs for Culturally Localized Generation","created":"2026-03-24","cited_by_count":4,"area":"mechinterp"},{"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":"2407.06902","title":"Learning From Crowdsourced Noisy Labels: A Signal Processing Perspective","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","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":"2512.08786","title":"A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs","created":"2025-12-09","cited_by_count":3,"area":"alignment"},{"id":"2602.00413","title":"Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation","created":"2026-01-31","cited_by_count":3,"area":"diffusion"},{"id":"2602.08716","title":"PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2410.18841","title":"From Efficiency to Equity: Measuring Fairness in Preference Learning","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2506.03619","title":"Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.20728","title":"Learning the Value Systems of Societies from Preferences","created":"2025-07-28","cited_by_count":2,"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":"2509.10685","title":"Pluralistic Alignment for Healthcare: A Role-Driven Framework","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.19104","title":"Online Distributionally Robust LLM Alignment via Regression to Relative Reward","created":"2025-09-23","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":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","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":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2606.04284","title":"Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling","created":"2026-06-02","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":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2412.16475","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","created":"2024-12-21","cited_by_count":1,"area":"alignment"},{"id":"2505.17380","title":"AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing","created":"2025-05-23","cited_by_count":1,"area":null},{"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":"2601.12091","title":"Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2602.06195","title":"DeDPO: Debiased Direct Preference Optimization for Diffusion Models","created":"2026-02-05","cited_by_count":1,"area":"diffusion"},{"id":"2602.20104","title":"Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.27141","title":"Routing Sensitivity Without Controllability: A Diagnostic Study of Fairness in MoE Language Models","created":"2026-03-28","cited_by_count":1,"area":"moe"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","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":"2605.05003","title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2605.16193","title":"Improving Cross-Cultural Survey Simulation with Calibrated Value Personas","created":"2026-05-15","cited_by_count":1,"area":null},{"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":"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":"2508.19132","title":"Active Query Selection for Crowd-Based Reinforcement Learning","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2509.08022","title":"DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2602.00485","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-01-31","cited_by_count":0,"area":"mllm"},{"id":"2602.08835","title":"Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2603.26922","title":"Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles","created":"2026-03-27","cited_by_count":0,"area":null},{"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":"2604.06621","title":"The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligence","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.20685","title":"MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment","created":"2026-04-22","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}