Imagen de Portada

UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Zelei, Cai, Xin-Qiang, Tang, Yuting, Zhang, Pushi, Yang, Boming, Sugiyama, Masashi, Xing, Xinyu
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MOA: Multi-Objective Alignment for Role-Playing Agents
por: Liao, Chonghua, et al.
Publicado: (2025)

Pareto Multi-Objective Alignment for Language Models
por: He, Qiang, et al.
Publicado: (2025)

Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
por: Li, Moxin, et al.
Publicado: (2025)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
por: Cai, Xin-Qiang, et al.
Publicado: (2026)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
por: Liu, Biao, et al.
Publicado: (2025)

Panacea: Pareto Alignment via Preference Adaptation for LLMs
por: Zhong, Yifan, et al.
Publicado: (2024)

Uncovering Cross-Objective Interference in Multi-Objective Alignment
por: Lu, Yining, et al.
Publicado: (2026)

A Survey on Explainable Deep Reinforcement Learning
por: Cheng, Zelei, et al.
Publicado: (2025)

Soft-Label Integration for Robust Toxicity Classification
por: Cheng, Zelei, et al.
Publicado: (2024)

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
por: Yu, Jiahao, et al.
Publicado: (2025)

Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective
por: Kou, Zhiqiang, et al.
Publicado: (2025)

MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment
por: Dou, Yipu, et al.
Publicado: (2026)

Pareto Optimal Code Generation
por: Orlanski, Gabriel, et al.
Publicado: (2025)

REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
por: Xu, Zhihao, et al.
Publicado: (2025)

Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning
por: Tang, Yuting, et al.
Publicado: (2024)

Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
por: Lu, Yining, et al.
Publicado: (2025)

Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
por: Ackermann, Johannes, et al.
Publicado: (2025)

Towards Scalable Oversight via Partitioned Human Supervision
por: Yin, Ren, et al.
Publicado: (2025)

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
por: Wang, Jikai, et al.
Publicado: (2025)

MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
por: Yang, Kailai, et al.
Publicado: (2024)

Reinforcement Learning from Bagged Reward
por: Tang, Yuting, et al.
Publicado: (2024)

Multi-Objective Alignment of Language Models for Personalized Psychotherapy
por: Beikzadeh, Mehrab, et al.
Publicado: (2026)

Robust Multi-Objective Preference Alignment with Online DPO
por: Gupta, Raghav, et al.
Publicado: (2025)

Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
por: Alqahtani, Sawsan, et al.
Publicado: (2021)

Towards Pareto Optimal Throughput in Small Language Model Serving
por: Recasens, Pol G., et al.
Publicado: (2024)

UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks
por: Marom, Ofir
Publicado: (2026)

ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data
por: Gu, Haoran, et al.
Publicado: (2025)

GPO: Learning from Critical Steps to Improve LLM Reasoning
por: Yu, Jiahao, et al.
Publicado: (2025)

Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
por: Wang, Bing, et al.
Publicado: (2026)

Improving LLM Safety Alignment with Dual-Objective Optimization
por: Zhao, Xuandong, et al.
Publicado: (2025)

Certifying Pareto-Optimality in Multi-Objective Maximum Satisfiability
por: Jabs, Christoph, et al.
Publicado: (2025)

Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
por: Ackermann, Johannes, et al.
Publicado: (2026)

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
por: Guo, Yiju, et al.
Publicado: (2024)

Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts
por: Fu, Tingchen, et al.
Publicado: (2024)

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
por: Bai, Yang, et al.
Publicado: (2026)

Pareto Optimal Learning for Estimating Large Language Model Errors
por: Zhao, Theodore, et al.
Publicado: (2023)

ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models
por: Bijoy, Biddut Sarker, et al.
Publicado: (2025)

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
por: Lin, Liang, et al.
Publicado: (2025)

One Model for All: Multi-Objective Controllable Language Models
por: He, Qiang, et al.
Publicado: (2026)

Offline Reinforcement Learning with Domain-Unlabeled Data
por: Nishimori, Soichiro, et al.
Publicado: (2024)