{"total":80,"rows":[{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"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":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"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":"2507.01915","title":"Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models","created":"2025-07-02","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":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"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":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2501.15167","title":"Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy","created":"2025-01-25","cited_by_count":16,"area":null},{"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":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"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":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2512.15146","title":"Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning","created":"2025-12-17","cited_by_count":13,"area":"lr"},{"id":"2507.10621","title":"Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats","created":"2025-07-14","cited_by_count":11,"area":"agents"},{"id":"2409.02969","title":"LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch","created":"2024-09-04","cited_by_count":10,"area":null},{"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":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"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":"2505.22086","title":"iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs","created":"2025-05-28","cited_by_count":7,"area":null},{"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":"2509.24696","title":"T-POP: Test-Time Personalization with Online Preference Feedback","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"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":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"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":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5,"area":"alignment"},{"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":"2404.00978","title":"Prior Constraints-based Reward Model Training for Aligning Large Language Models","created":"2024-04-01","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":"2502.02444","title":"Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models","created":"2025-02-04","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":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2503.14321","title":"COPA: Comparing the incomparable in multi-objective model evaluation","created":"2025-03-18","cited_by_count":3,"area":null},{"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":"2510.11952","title":"GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences","created":"2025-10-13","cited_by_count":3,"area":null},{"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":"2606.05523","title":"CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning","created":"2026-06-04","cited_by_count":3,"area":"alignment"},{"id":"2412.11145","title":"The Superalignment of Superhuman Intelligence with Large Language Models","created":"2024-12-15","cited_by_count":2,"area":"mllm"},{"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":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"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":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2604.05965","title":"Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment","created":"2026-04-07","cited_by_count":2,"area":"alignment"},{"id":"2604.20816","title":"ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control","created":"2026-04-22","cited_by_count":2,"area":"diffusion"},{"id":"2606.16111","title":"Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2512.06515","title":"ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2602.09689","title":"Model soups need only one ingredient","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.00047","title":"What Is the Alignment Tax?","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.02229","title":"Safety Training May Persist Through Helpfulness Optimization in LLM Agents","created":"2026-02-13","cited_by_count":1,"area":"agents"},{"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":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","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":"2606.19744","title":"Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings","created":"2026-06-18","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":"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":"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"},{"id":"2605.12682","title":"Learning Transferable Latent User Preferences for Human-Aligned Decision Making","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.25342","title":"MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2607.18258","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.12704","title":"Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2608.29378","title":"Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2608.29978","title":"Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.05992","title":"MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04845","title":"Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}