English
Related papers

Related papers: Mitigating Reward Over-optimization in Direct Alig…

200 papers

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Machine Learning · Computer Science 2025-10-28 Junkang Wu , Kexin Huang , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

Computation and Language · Computer Science 2025-04-30 Kian Ahrabian , Xihui Lin , Barun Patra , Vishrav Chaudhary , Alon Benhaim , Jay Pujara , Xia Song

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

Direct preference optimization (DPO) is widely used as a simple and stable method for aligning large language models (LLMs) with human preferences. This paper investigates a generalized DPO loss that enables a policy model to match the…

Machine Learning · Computer Science 2025-10-28 Yeongmin Kim , Heesun Bae , Byeonghu Na , Il-Chul Moon

Recent advances in diffusion models have improved Real-World Image Super-Resolution (Real-ISR), but existing methods lack human feedback integration, risking misalignment with human preference and may leading to artifacts, hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Miaomiao Cai , Simiao Li , Wei Li , Xudong Huang , Hanting Chen , Jie Hu , Yunhe Wang

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Machine Learning · Computer Science 2024-05-02 Wei Xiong , Hanze Dong , Chenlu Ye , Ziqi Wang , Han Zhong , Heng Ji , Nan Jiang , Tong Zhang

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models (LLMs) with human preferences, bypassing the need for a learned reward model. Despite its growing adoption, a fundamental…

Machine Learning · Computer Science 2025-11-10 Yu Pan , Zhongze Cai , Guanting Chen , Huaiyang Zhong , Chonghuan Wang

The emergence of large Vision Language Models (VLMs) has broadened the scope and capabilities of single-modal Large Language Models (LLMs) by integrating visual modalities, thereby unlocking transformative cross-modal applications in a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Shuo Xing , Peiran Li , Yuping Wang , Ruizheng Bai , Yueqi Wang , Chan-Wei Hu , Chengxuan Qian , Huaxiu Yao , Zhengzhong Tu

Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large language and…

Artificial Intelligence · Computer Science 2025-12-16 Zihui Zhao , Zechang Li

Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…

Machine Learning · Computer Science 2025-10-01 Frédéric Berdoz , Luca A. Lanzendörfer , René Caky , Roger Wattenhofer

Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation with the alleviation of compounding errors, offering a means…

Computation and Language · Computer Science 2025-02-25 Wentao Shi , Mengqi Yuan , Junkang Wu , Qifan Wang , Fuli Feng

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Machine Learning · Computer Science 2025-09-09 Thanh Thi Nguyen , Campbell Wilson , Janis Dalins

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

Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that…

Machine Learning · Computer Science 2023-11-27 Zhuoying Chen , Huiping Li , Zhaoxu Wang

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 been critical to the success of the latest generation of generative AI models. In response to the complex nature of the classical RLHF pipeline, direct alignment algorithms such as…

Machine Learning · Computer Science 2024-08-14 Rafael Rafailov , Joey Hejna , Ryan Park , Chelsea Finn

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbalanced responsiveness to the data of varying hardness,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Jinda Lu , Junkang Wu , Jinghan Li , Xiaojun Jia , Shuo Wang , YiFan Zhang , Junfeng Fang , Xiang Wang , Xiangnan He