{"total":107,"rows":[{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"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":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44,"area":"alignment"},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"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":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2410.13116","title":"Learning to Summarize from LLM-generated Feedback","created":"2024-10-17","cited_by_count":24,"area":"alignment"},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"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":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16,"area":"lr"},{"id":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2410.15483","title":"Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective","created":"2024-10-20","cited_by_count":12,"area":"alignment"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11,"area":null},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2509.21528","title":"Preemptive Detection and Steering of LLM Misalignment via Latent Reachability","created":"2025-09-25","cited_by_count":10,"area":"alignment"},{"id":"2404.04920","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment","created":"2024-04-07","cited_by_count":9,"area":"diffusion"},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2405.11870","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","created":"2024-05-20","cited_by_count":8,"area":"alignment"},{"id":"2410.14676","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","created":"2024-10-18","cited_by_count":8,"area":"alignment"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2505.18547","title":"Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models","created":"2025-05-24","cited_by_count":7,"area":"diffusion"},{"id":"2509.24610","title":"OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2510.14008","title":"Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment","created":"2025-10-15","cited_by_count":7,"area":"agents"},{"id":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6,"area":"alignment"},{"id":"2410.19720","title":"2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision","created":"2024-10-25","cited_by_count":6,"area":"alignment"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2506.07165","title":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","created":"2025-06-08","cited_by_count":6,"area":"alignment"},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","cited_by_count":6,"area":"alignment"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"id":"2410.08316","title":"COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework","created":"2024-10-10","cited_by_count":5,"area":"alignment"},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","cited_by_count":5,"area":"alignment"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2510.22085","title":"Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models","created":"2025-10-24","cited_by_count":5,"area":"safety"},{"id":"2601.00268","title":"Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity","created":"2026-01-01","cited_by_count":5,"area":"agents"},{"id":"2405.17956","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier","created":"2024-05-28","cited_by_count":4,"area":"alignment"},{"id":"2412.13998","title":"Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes","created":"2024-12-18","cited_by_count":4,"area":"alignment"},{"id":"2503.04113","title":"Uncovering Gaps in How Humans and LLMs Interpret Subjective Language","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.21332","title":"ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2512.10575","title":"RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems","created":"2025-12-11","cited_by_count":4,"area":"alignment"},{"id":"2410.21533","title":"L3Ms -- Lagrange Large Language Models","created":"2024-10-28","cited_by_count":3,"area":"alignment"},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2506.17231","title":"Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs","created":"2025-05-26","cited_by_count":3,"area":"safety"},{"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":"2511.07691","title":"CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences","created":"2025-11-10","cited_by_count":3,"area":"alignment"},{"id":"2602.09538","title":"UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"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":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2410.19206","title":"Inference time LLM alignment in single and multidomain preference spectrum","created":"2024-10-24","cited_by_count":2,"area":"alignment"},{"id":"2502.02628","title":"e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration","created":"2025-02-04","cited_by_count":2,"area":"alignment"},{"id":"2505.20336","title":"MOSLIM:Align with diverse preferences in prompts through reward classification","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2507.02255","title":"Listwise Preference Alignment Optimization for Tail Item Recommendation","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2602.00453","title":"FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2503.08849","title":"Learning Pareto manifolds in high dimensions: How can regularization help?","created":"2025-03-11","cited_by_count":1,"area":null},{"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":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2512.06515","title":"ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"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":"2604.04497","title":"One Model for All: Multi-Objective Controllable Language Models","created":"2026-04-06","cited_by_count":1,"area":"alignment"},{"id":"2604.24826","title":"A Comparative Evaluation of AI Agent Security Guardrails","created":"2026-04-27","cited_by_count":1,"area":"safety"},{"id":"2605.11679","title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.24154","title":"Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs","created":"2026-05-22","cited_by_count":1,"area":"alignment"},{"id":"2607.24900","title":"Inverse RL Helps Align AI by Imitating Humans","created":"2026-07-27","cited_by_count":1,"area":"alignment"},{"id":"2608.16553","title":"STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2609.08064","title":"Risk-Conditioned Fine-Tuning of Large Language Models","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2412.16378","title":"REFA: Reference Free Alignment for multi-preference optimization","created":"2024-12-20","cited_by_count":0,"area":"alignment"},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.06552","title":"References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation","created":"2025-05-10","cited_by_count":0,"area":"alignment"},{"id":"2511.20736","title":"Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2601.03273","title":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness","created":"2025-12-22","cited_by_count":0,"area":"safety"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}