English
Related papers

Related papers: Improving Safety Alignment via Balanced Direct Pre…

200 papers

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Artificial Intelligence · Computer Science 2026-03-02 Xiaoyang Cao , Zelai Xu , Mo Guang , Kaiwen Long , Michiel A. Bakker , Yu Wang , Chao Yu

Social agents powered by large language models (LLMs) can simulate human social behaviors but fall short in handling complex social dialogues. Direct Preference Optimization (DPO) has proven effective in aligning LLM behavior with human…

Artificial Intelligence · Computer Science 2025-02-28 Aobo Kong , Wentao Ma , Shiwan Zhao , Yongbin Li , Yuchuan Wu , Ke Wang , Xiaoqian Liu , Qicheng Li , Yong Qin , Fei Huang

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

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Machine Learning · Computer Science 2024-06-06 Andi Nika , Debmalya Mandal , Parameswaran Kamalaruban , Georgios Tzannetos , Goran Radanović , Adish Singla

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

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

Machine Learning · Computer Science 2026-02-03 Mete Erdogan

In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback…

Information Retrieval · Computer Science 2026-05-04 Xingyu Hu , Kai Zhang , Jiancan Wu , Shuli Wang , Chi Wang , Wenshuai Chen , Yinhua Zhu , Haitao Wang , Xingxing Wang , Xiang Wang

Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce hallucinations when preference judgments reward fluency and confidence over factual correctness.…

Computation and Language · Computer Science 2026-04-16 Sindhuja Chaduvula , Ahmed Y. Radwan , Azib Farooq , Yani Ioannou , Shaina Raza

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

Computation and Language · Computer Science 2024-09-20 Jinchuan Tian , Chunlei Zhang , Jiatong Shi , Hao Zhang , Jianwei Yu , Shinji Watanabe , Dong Yu

Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers…

Computation and Language · Computer Science 2025-02-21 Ruichen Shao , Bei Li , Gangao Liu , Yang Chen , Xiang Zhou , Jingang Wang , Xunliang Cai , Peng Li

Direct Preference Optimization (DPO) and its variants have become standard for aligning Large Language Models due to their simplicity and offline stability. However, we identify two fundamental limitations. First, the optimal policy depends…

Artificial Intelligence · Computer Science 2026-02-10 Yu Li , Tian Lan , Zhengling Qi

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

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

Computation and Language · Computer Science 2024-06-18 Jie Liu , Zhanhui Zhou , Jiaheng Liu , Xingyuan Bu , Chao Yang , Han-Sen Zhong , Wanli Ouyang

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Computation and Language · Computer Science 2024-12-31 Jingyuan Ma , Rui Li , Zheng Li , Lei Sha , Zhifang Sui

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Machine Learning · Computer Science 2025-12-09 Moxin Li , Yuantao Zhang , Wenjie Wang , Wentao Shi , Zhuo Liu , Fuli Feng , Tat-Seng Chua

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

Machine Learning · Computer Science 2025-04-21 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jiawei Chen , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline…

Machine Learning · Computer Science 2024-10-23 Wenda Xu , Jiachen Li , William Yang Wang , Lei Li

Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse preference data, causing…

Machine Learning · Computer Science 2025-10-08 Hyung Gyu Rho