English
Related papers

Related papers: Enhancing LLM Safety via Constrained Direct Prefer…

200 papers

Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations about \texttt{DPO}. First, we show that \texttt{DPO} loss…

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Machine Learning · Computer Science 2024-07-01 William Muldrew , Peter Hayes , Mingtian Zhang , David Barber

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

Machine Learning · Computer Science 2025-07-22 Junkang Wu , Xue Wang , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback…

Artificial Intelligence · Computer Science 2024-09-02 Shiming Xie , Hong Chen , Fred Yu , Zeye Sun , Xiuyu Wu , Yingfan Hu

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Computation and Language · Computer Science 2026-05-19 Xuan Qi , Rongwu Xu , Zhijing Jin

Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. However, proximal policy optimization (PPO) based RLHF is occasionally unstable requiring significant…

Computation and Language · Computer Science 2024-04-02 Saeed Khaki , JinJin Li , Lan Ma , Liu Yang , Prathap Ramachandra

Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free.…

Computation and Language · Computer Science 2024-10-11 Shusheng Xu , Wei Fu , Jiaxuan Gao , Wenjie Ye , Weilin Liu , Zhiyu Mei , Guangju Wang , Chao Yu , Yi Wu

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

Machine Learning · Computer Science 2025-02-12 Kaixuan Ji , Jiafan He , Quanquan Gu

Direct Preference Optimization (DPO) is an efficient alignment technique that steers LLMs towards preferable outputs by training on preference data, bypassing the need for explicit reward models. Its simplicity enables easy adaptation to…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Computation and Language · Computer Science 2026-01-01 Junshu Pan , Wei Shen , Shulin Huang , Qiji Zhou , Yue Zhang

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei

With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be…

Machine Learning · Computer Science 2025-02-06 Xuerui Su , Yue Wang , Jinhua Zhu , Mingyang Yi , Feng Xu , Zhiming Ma , Yuting Liu

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Machine Learning · Computer Science 2025-10-21 Keertana Chidambaram , Karthik Vinay Seetharaman , Vasilis Syrgkanis

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Computation and Language · Computer Science 2024-09-27 Jian Li , Haojing Huang , Yujia Zhang , Pengfei Xu , Xi Chen , Rui Song , Lida Shi , Jingwen Wang , Hao Xu

Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy.…

Machine Learning · Computer Science 2024-12-02 Wei Liu , Yang Bai , Chengcheng Han , Rongxiang Weng , Jun Xu , Xuezhi Cao , Jingang Wang , Xunliang Cai