English
Related papers

Related papers: Gradient-Gated DPO: Stabilizing Preference Optimiz…

200 papers

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

Machine Learning · Computer Science 2024-07-31 Rafael Rafailov , Archit Sharma , Eric Mitchell , Stefano Ermon , Christopher D. Manning , Chelsea Finn

Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter…

Artificial Intelligence · Computer Science 2024-10-15 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

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

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Ruojun Xu , Yu Kai , Xuhua Ren , Jiaxiang Cheng , Bing Ma , Tianxiang Zheng , Qinhlin Lu

Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when…

Computation and Language · Computer Science 2024-07-15 Xiangkun Hu , Tong He , David Wipf

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 predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Khiem Pham , Quang Nguyen , Tung Nguyen , Jingsen Zhu , Michele Santacatterina , Dimitris Metaxas , Ramin Zabih

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

Machine Learning · Computer Science 2024-03-06 Zixuan Liu , Xiaolin Sun , Zizhan Zheng

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Computation and Language · Computer Science 2025-10-27 Weibin Liao , Xu Chu , Yasha Wang

Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this…

Machine Learning · Computer Science 2026-05-27 Jilong Liu , Yonghui Yang , Pengyang Shao , Wenjian Tao , Hao Zhan , Haokai Ma , Wei Qin , Richang Hong

Direct Preference Optimization (DPO) has recently emerged as a simple and effective alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with user preferences. However, existing DPO…

Machine Learning · Computer Science 2025-10-10 Jason Bohne , Pawel Polak , David Rosenberg , Brian Bloniarz , Gary Kazantsev

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

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…

Machine Learning · Computer Science 2024-06-28 Xin Lai , Zhuotao Tian , Yukang Chen , Senqiao Yang , Xiangru Peng , Jiaya Jia

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an…

Artificial Intelligence · Computer Science 2025-07-15 Wenyi Xiao , Zechuan Wang , Leilei Gan , Shuai Zhao , Zongrui Li , Ruirui Lei , Wanggui He , Luu Anh Tuan , Long Chen , Hao Jiang , Zhou Zhao , Fei Wu

Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first erroneous step in the reasoning chain. However, they…

Computation and Language · Computer Science 2025-02-21 Huimin Xu , Xin Mao , Feng-Lin Li , Xiaobao Wu , Wang Chen , Wei Zhang , Anh Tuan Luu

Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, existing work rarely examines how Direct Preference…

Information Retrieval · Computer Science 2026-04-01 Hejin Huang , Jusheng Zhang , Kaitong Cai , Jian Wang , Rong Pan

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Computation and Language · Computer Science 2025-05-27 Yeyuan Wang , Dehong Gao , Rujiao Long , Lei Yi , Linbo Jin , Libin Yang , Xiaoyan Cai

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu