{"total":31,"rows":[{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"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":"2502.17086","title":"Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2502.11767","title":"From Selection to Generation: A Survey of LLM-based Active Learning","created":"2025-02-17","cited_by_count":19,"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":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2509.25137","title":"The Era of Real-World Human Interaction: RL from User Conversations","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2505.13355","title":"Survey: Multi-Armed Bandits Meet Large Language Models","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2511.19356","title":"Rethinking Reward Signals in Video GRPO: When Scores Become Targets","created":"2025-11-24","cited_by_count":6,"area":null},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","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":"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":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2609.04738","title":"Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.08064","title":"Risk-Conditioned Fine-Tuning of Large Language Models","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2508.10030","title":"Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.20619","title":"SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2608.09507","title":"Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.23783","title":"Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.01573","title":"Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.15094","title":"Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}