English
Related papers

Related papers: Aligning Language Models with Preferences through …

200 papers

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

Computation and Language · Computer Science 2024-06-03 Runsheng Yu , Yong Wang , Xiaoqi Jiao , Youzhi Zhang , James T. Kwok

Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. In theory, diffusion models…

Machine Learning · Computer Science 2026-05-14 Xiang Li , Yixuan Jia , Xiao Li , Jeffrey A. Fessler , Rongrong Wang , Qing Qu

While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Yihong Luo , Tianyang Hu , Yifan Song , Jiacheng Sun , Zhenguo Li , Jing Tang

Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback…

Information Retrieval · Computer Science 2025-12-17 Jiacong Zhou , Xianyun Wang , Min Zhang , Jun Yu

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Typically, RLHF involves the initial step of learning a reward model from human feedback,…

Domain adaptation is an important problem and often needed for real-world applications. In this problem, instead of i.i.d. training and testing datapoints, we assume that the source (training) data and the target (testing) data have…

Machine Learning · Computer Science 2022-03-15 A. Tuan Nguyen , Toan Tran , Yarin Gal , Philip H. S. Torr , Atılım Güneş Baydin

The family of f-divergences is ubiquitously applied to generative modeling in order to adapt the distribution of the model to that of the data. Well-definedness of f-divergences, however, requires the distributions of the data and model to…

Machine Learning · Statistics 2019-06-04 Akash Srivastava , Kristjan Greenewald , Farzaneh Mirzazadeh

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

Artificial Intelligence · Computer Science 2024-10-23 Pietro Bernardelle , Gianluca Demartini

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Artificial Intelligence · Computer Science 2026-03-25 Shiji Zhao , Mengyang Wang , Shukun Xiong , Fangzhou Chen , Qihui Zhu , Shouwei Ruan , Yisong Xiao , Ranjie Duan , Xun Chen , XingXing Wei

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seokhun Ju , Seungyub Han , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee

The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but…

We propose a new neural sequence model training method in which the objective function is defined by $\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning…

Machine Learning · Statistics 2017-07-03 Sotetsu Koyamada , Yuta Kikuchi , Atsunori Kanemura , Shin-ichi Maeda , Shin Ishii

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

Artificial Intelligence · Computer Science 2024-07-08 Jin Peng Zhou , Katie Z Luo , Jingwen Gu , Jason Yuan , Kilian Q. Weinberger , Wen Sun

Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference…

Computation and Language · Computer Science 2024-06-10 Michael J. Ryan , William Held , Diyi Yang

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Artificial Intelligence · Computer Science 2024-11-01 Debangshu Banerjee , Aditya Gopalan

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Preeti Lamba , Kiran Ravish , Ankita Kushwaha , Pawan Kumar

The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the training process progresses, the output distribution of the…

Machine Learning · Computer Science 2024-05-02 Shihan Dou , Yan Liu , Enyu Zhou , Tianlong Li , Haoxiang Jia , Limao Xiong , Xin Zhao , Junjie Ye , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We…

Computation and Language · Computer Science 2025-12-17 Mahmoud Srewa , Tianyu Zhao , Salma Elmalaki

Reinforcement Learning from human feedback (RLHF) has been shown a promising direction for aligning generative models with human intent and has also been explored in recent works for alignment of diffusion generative models. In this work,…

Machine Learning · Computer Science 2024-09-16 Hanyang Zhao , Haoxian Chen , Ji Zhang , David D. Yao , Wenpin Tang