English
Related papers

Related papers: Learning to Optimize Multi-Objective Alignment Thr…

200 papers

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy…

Computation and Language · Computer Science 2026-05-26 Guochao Jiang , Jingyi Song , Guofeng Quan , Chuzhan Hao , Guohua Liu , Yuewei Zhang

Real-world problems are often multi-objective with decision-makers unable to specify a priori which trade-off between the conflicting objectives is preferable. Intuitively, building machine learning solutions in such cases would entail…

Machine Learning · Computer Science 2021-10-20 Timo M. Deist , Monika Grewal , Frank J. W. M. Dankers , Tanja Alderliesten , Peter A. N. Bosman

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the…

In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four…

Machine Learning · Computer Science 2025-03-03 Giseung Park , Youngchul Sung

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring…

Robotics · Computer Science 2025-05-30 Lucas N. Alegre , Agon Serifi , Ruben Grandia , David Müller , Espen Knoop , Moritz Bächer

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Dongliang Chen , Xinlin Zhuang , Junjie Xu , Luojian Xie , Zehui Wang , Jiaxi Zhuang , Haolin Yang , Liang Dou , Xiao He , Xingjiao Wu , Ying Qian

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

Computation and Language · Computer Science 2026-05-26 Linhao Luo , Thuy-Trang Vu , Van-Anh Nguyen , Junae Kim , Gholamreza Haffari , Dinh Phung

Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized…

Machine Learning · Computer Science 2019-05-14 Axel Abels , Diederik M. Roijers , Tom Lenaerts , Ann Nowé , Denis Steckelmacher

With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention. It is a common paradigm in object detection frameworks to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Yihao Luo , Xiang Cao , Juntao Zhang , Peng Cheng , Tianjiang Wang , Qi Feng

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly…

Artificial Intelligence · Computer Science 2023-10-10 Marcin Korecki , Damian Dailisan , Cesare Carissimo

Deep reinforcement learning (DRL) has recently shown its success in tackling complex combinatorial optimization problems. When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to…

Artificial Intelligence · Computer Science 2022-02-15 Zizhen Zhang , Zhiyuan Wu , Hang Zhang , Jiahai Wang

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…

Machine Learning · Computer Science 2026-01-01 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Effective evaluation of real-time strategy tasks requires adaptive mechanisms to cope with dynamic and unpredictable environments. This study proposes a method to improve evaluation functions for real-time responsiveness to battle-field…

Artificial Intelligence · Computer Science 2025-01-08 Weilong Yang , Jie Zhang , Xunyun Liu , Yanqing Ye

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight…

Machine Learning · Computer Science 2026-04-28 Wenzhe Xu , Biao Liu , Yiyang Sun , Xin Geng , Ning Xu

Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward formulations, obtained by aggregating these…

Machine Learning · Computer Science 2026-01-27 Deepthi Pathare , Leo Laine , Morteza Haghir Chehreghani

RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with…

Computation and Language · Computer Science 2025-06-10 Yasaman Jafari , Dheeraj Mekala , Rose Yu , Taylor Berg-Kirkpatrick

Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can…

Computation and Language · Computer Science 2026-05-26 Peter Chen , Xiaopeng Li , Xi Chen , Tianyi Lin

Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are…

Information Retrieval · Computer Science 2026-02-13 Pan Li , Alexander Tuzhilin

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao
‹ Prev 1 2 3 10 Next ›