English
Related papers

Related papers: Generalized Preference Optimization: A Unified App…

200 papers

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Machine Learning · Computer Science 2026-05-21 Zhanhong Jiang

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Artificial Intelligence · Computer Science 2026-05-21 Zhiqin Yang , Yonggang Zhang , Wei Xue , Dong Fang , Bo Han , Yike Guo

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Machine Learning · Computer Science 2026-05-18 Yue Wang , Qizhou Wang , Zizhuo Zhang , Gang Niu , Bo Han , Masashi Sugiyama

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Machine Learning · Computer Science 2024-11-12 Zhuotong Chen , Fang Liu , Jennifer Zhu , Wanyu Du , Yanjun Qi

DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have…

Computation and Language · Computer Science 2025-08-26 Chenxu Yang , Ruipeng Jia , Naibin Gu , Zheng Lin , Siyuan Chen , Chao Pang , Weichong Yin , Yu Sun , Hua Wu , Weiping Wang

Direct preference optimization (DPO) is widely used as a simple and stable method for aligning large language models (LLMs) with human preferences. This paper investigates a generalized DPO loss that enables a policy model to match the…

Machine Learning · Computer Science 2025-10-28 Yeongmin Kim , Heesun Bae , Byeonghu Na , Il-Chul Moon

In this note, we examine the aggregation of preferences achieved by the Group Policy Optimisation (GRPO) algorithm, a reinforcement learning method used to train advanced artificial intelligence models such as DeepSeek-R1-Zero and…

Machine Learning · Computer Science 2025-03-14 Milan Vojnovic , Se-Young Yun

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Computation and Language · Computer Science 2024-10-14 Yiju Guo , Ganqu Cui , Lifan Yuan , Ning Ding , Zexu Sun , Bowen Sun , Huimin Chen , Ruobing Xie , Jie Zhou , Yankai Lin , Zhiyuan Liu , Maosong Sun

Two divergence regimes dominate modern alignment practice. Supervised fine-tuning and many distillation-style objectives implicitly minimize the forward KL divergence KL(q || pi_theta), yielding stable mode-covering updates but often…

Machine Learning · Computer Science 2025-12-30 Wang Zixian

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

In this paper, we theoretically study the offline alignment of language models with human preference feedback, under both preference label corruption and privacy protections. To this end, we propose Square$\chi$PO, a simple one-line change…

Machine Learning · Computer Science 2025-05-28 Xingyu Zhou , Yulian Wu , Wenqian Weng , Francesco Orabona

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

Artificial Intelligence · Computer Science 2024-10-22 Oh Joon Kwon , Daiki E. Matsunaga , Kee-Eung Kim

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods…

Machine Learning · Computer Science 2026-04-29 Peng Liao , Peijia Zheng , Lingbo Li , Shangsong Liang , Lin Chen

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Computation and Language · Computer Science 2024-05-29 Yueqin Yin , Zhendong Wang , Yi Gu , Hai Huang , Weizhu Chen , Mingyuan Zhou

Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning, one of the most popular approaches, stands out for its efficiency in reward modeling.…

Machine Learning · Computer Science 2026-05-26 Xiaobo Wang , Zixia Jia , Jiaqi Li , Qi Liu , Zilong Zheng

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

Machine Learning · Computer Science 2026-05-25 Miria Feng , Mert Pilanci

Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations about \texttt{DPO}. First, we show that \texttt{DPO} loss…

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu