English
Related papers

Related papers: Minor DPO reject penalty to increase training robu…

200 papers

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Computation and Language · Computer Science 2025-06-05 Honggen Zhang , Xufeng Zhao , Igor Molybog , June Zhang

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

DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analysis uncovers an asymmetric gradient behavior in DPO: the loss…

Computation and Language · Computer Science 2026-05-28 Shaolong Chen , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps:…

Machine Learning · Computer Science 2024-04-17 Jonathan D. Chang , Wenhao Zhan , Owen Oertell , Kianté Brantley , Dipendra Misra , Jason D. Lee , Wen Sun

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this…

Computation and Language · Computer Science 2025-07-23 Tianze Wang , Dongnan Gui , Yifan Hu , Shuhang Lin , Linjun Zhang

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific…

Machine Learning · Computer Science 2025-10-07 Kai Qin , Jiaqi Wu , Jianxiang He , Haoyuan Sun , Yifei Zhao , Bin Liang , Yongzhe Chang , Tiantian Zhang , Houde Liu

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses equally, neglecting the differing importance of individual…

Computation and Language · Computer Science 2026-05-27 Chengyu Huang , Zhuohang Li , Sheng-Yen Chou , Claire Cardie

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this…

Computation and Language · Computer Science 2024-11-05 Yu Meng , Mengzhou Xia , Danqi Chen

The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences.…

Artificial Intelligence · Computer Science 2026-01-28 Zetian Sun , Dongfang Li , Xuhui Chen , Baotian Hu , Min Zhang

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to…

Machine Learning · Computer Science 2024-03-26 Kai Yang , Jian Tao , Jiafei Lyu , Chunjiang Ge , Jiaxin Chen , Qimai Li , Weihan Shen , Xiaolong Zhu , Xiu Li

Bootstrapping large language models (LLMs) through preference-based policy optimization offers a promising direction for aligning model behavior with human preferences without relying on extensive manual annotations. In this work, we…

Artificial Intelligence · Computer Science 2025-12-25 Chen Jia

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 emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally,…

Machine Learning · Computer Science 2026-05-26 Shangpin Peng , Weinong Wang , Zhuotao Tian , Senqiao Yang , Xing Wu , Haotian Xu , Chengquan Zhang , Takashi Isobe , Baotian Hu , Min Zhang

Large Language Models (LLMs) have exhibited remarkable performance across a wide range of domains, motivating research into their potential for recommendation systems. Early efforts have leveraged LLMs' rich knowledge and strong…

Information Retrieval · Computer Science 2025-04-03 Chao Sun , Yaobo Liang , Yaming Yang , Shilin Xu , Tianmeng Yang , Yunhai Tong

Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise…

Machine Learning · Computer Science 2026-05-05 Inoussa Mouiche

Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that…

Computation and Language · Computer Science 2026-05-13 Qiming Bao , Juho Leinonen , Paul Denny , Michael J. Witbrock

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

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

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing…

Computation and Language · Computer Science 2024-10-01 Shitong Duan , Xiaoyuan Yi , Peng Zhang , Yan Liu , Zheng Liu , Tun Lu , Xing Xie , Ning Gu

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song