English
Related papers

Related papers: Learning Where It Matters: Geometric Anchoring for…

200 papers

Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains are highly impactful.…

Computation and Language · Computer Science 2025-11-18 Ruibo Deng , Duanyu Feng , Wenqiang Lei

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…

Machine Learning · Computer Science 2026-01-22 Yuhui Sun , Xiyao Wang , Zixi Li , YiTian Ding , Tianyang Ling , Jialuo Chen , Tianyi Yu , Zhenlong Yuan , Jinman Zhao

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

Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through…

Computation and Language · Computer Science 2025-06-05 Lin Sun , Chuang Liu , Peng Liu , Bingyang Li , Weijia Lu , Ning Wu

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

Computation and Language · Computer Science 2025-05-30 Gengxu Li , Tingyu Xia , Yi Chang , Yuan Wu

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

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

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

Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy…

Computation and Language · Computer Science 2025-10-21 Yuzhong Zhao , Yue Liu , Junpeng Liu , Jingye Chen , Xun Wu , Yaru Hao , Tengchao Lv , Shaohan Huang , Lei Cui , Qixiang Ye , Fang Wan , Furu Wei

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

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

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Machine Learning · Computer Science 2026-05-22 Yonghui Yang , Wenjian Tao , Jilong Liu , Xingyu Zhu , Junfeng Fang , Weibiao Huang , Le Wu , Richang Hong , Tat-Sent Chua

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 algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcement learning with human feedback (RLHF). We show that DPO…

Machine Learning · Computer Science 2025-10-24 Aditya Gopalan , Sayak Ray Chowdhury , Debangshu Banerjee

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a critical tension. DPO weighs each update relative to a…

Machine Learning · Computer Science 2026-02-13 Suqin Yuan , Xingrui Yu , Jiyang Zheng , Lei Feng , Dadong Wang , Ivor Tsang , Tongliang Liu

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 Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training…

Machine Learning · Computer Science 2026-05-11 Ning Liu , Chuanneng Sun , Kristina Klinkner , Shervin Malmasi