English
Related papers

Related papers: Preference as Reward, Maximum Preference Optimizat…

200 papers

Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be sensitive to noise in the data and prone to overfitting.…

Machine Learning · Computer Science 2025-10-28 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To…

Computation and Language · Computer Science 2024-06-03 Yueqin Yin , Zhendong Wang , Yujia Xie , Weizhu Chen , Mingyuan Zhou

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One…

Machine Learning · Computer Science 2025-06-10 Chuheng Zhang , Wei Shen , Li Zhao , Xuyun Zhang , Xiaolong Xu , Wanchun Dou , Jiang Bian

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

Machine Learning · Computer Science 2025-02-10 Ryan Bahlous-Boldi , Li Ding , Lee Spector , Scott Niekum

Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood difference between chosen and rejected responses. However,…

Computation and Language · Computer Science 2025-05-27 Meng Li , Guangda Huzhang , Haibo Zhang , Xiting Wang , Anxiang Zeng

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be…

Machine Learning · Computer Science 2025-02-10 Chenjia Bai , Yang Zhang , Shuang Qiu , Qiaosheng Zhang , Kang Xu , Xuelong Li

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RLHF) proves effective, it is complicated and highly…

Computation and Language · Computer Science 2024-10-31 Shiqi Wang , Zhengze Zhang , Rui Zhao , Fei Tan , Cam Tu Nguyen

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

Computation and Language · Computer Science 2025-10-16 Hao Wang , Linlong Xu , Heng Liu , Yangyang Liu , Xiaohu Zhao , Bo Zeng , Liangying Shao , Longyue Wang , Weihua Luo , Kaifu Zhang

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…

Computation and Language · Computer Science 2026-03-03 Aladin Djuhera , Farhan Ahmed , Swanand Ravindra Kadhe , Syed Zawad , Heiko Ludwig , Holger Boche

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such…

Machine Learning · Computer Science 2025-09-09 Junda Wu , Rohan Surana , Zhouhang Xie , Yiran Shen , Yu Xia , Tong Yu , Ryan A. Rossi , Prithviraj Ammanabrolu , Julian McAuley

Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-based, following the Bradley-Terry (BT) model assumption,…

Machine Learning · Computer Science 2025-03-04 Yuheng Zhang , Dian Yu , Baolin Peng , Linfeng Song , Ye Tian , Mingyue Huo , Nan Jiang , Haitao Mi , Dong Yu

We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO). Our study decomposes this gap into two sources: the explicit…

Machine Learning · Computer Science 2026-05-13 Ruizhe Shi , Minhak Song , Runlong Zhou , Zihan Zhang , Maryam Fazel , Simon S. Du

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

Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the…

Artificial Intelligence · Computer Science 2025-02-19 Audrey Huang , Wenhao Zhan , Tengyang Xie , Jason D. Lee , Wen Sun , Akshay Krishnamurthy , Dylan J. Foster

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Computation and Language · Computer Science 2025-06-13 Hee Suk Yoon , Eunseop Yoon , Mark Hasegawa-Johnson , Sungwoong Kim , Chang D. Yoo

As large language models increasingly drive real-world applications, aligning them with human values becomes paramount. Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique, translating preference data into…

Machine Learning · Computer Science 2025-02-07 Yunzhen Feng , Ariel Kwiatkowski , Kunhao Zheng , Julia Kempe , Yaqi Duan

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yi-Lun Wu , Bo-Kai Ruan , Chiang Tseng , Hong-Han Shuai