English
Related papers

Related papers: Unpacking DPO and PPO: Disentangling Best Practice…

200 papers

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Computation and Language · Computer Science 2026-04-03 Simona-Vasilica Oprea , Adela Bâra

How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a…

Computation and Language · Computer Science 2024-05-28 Hung Le , Quan Tran , Dung Nguyen , Kien Do , Saloni Mittal , Kelechi Ogueji , Svetha Venkatesh

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

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Ruojun Xu , Yu Kai , Xuhua Ren , Jiaxiang Cheng , Bing Ma , Tianxiang Zheng , Qinhlin Lu

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning…

Machine Learning · Computer Science 2025-07-01 Yi Ren , Danica J. Sutherland

Reinforcement Learning from Human Feedback (RLHF) has been a crucial component in the recent success of Large Language Models. However, RLHF is know to exploit biases in human preferences, such as verbosity. A well-formatted and eloquent…

Computation and Language · Computer Science 2024-09-10 Ryan Park , Rafael Rafailov , Stefano Ermon , Chelsea Finn

Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual…

Computation and Language · Computer Science 2024-04-04 Renjie Pi , Tianyang Han , Wei Xiong , Jipeng Zhang , Runtao Liu , Rui Pan , Tong Zhang

Varied approaches for aligning language models have been proposed, including supervised fine-tuning, RLHF, and direct optimization methods such as DPO. Although DPO has rapidly gained popularity due to its straightforward training process…

Computation and Language · Computer Science 2024-08-08 Prasann Singhal , Nathan Lambert , Scott Niekum , Tanya Goyal , Greg Durrett

Recent research has attempted to associate preference optimization (PO) performance with the underlying preference datasets. In this work, our observation is that the differences between the preferred response $y^+$ and dispreferred…

Computation and Language · Computer Science 2025-11-18 Chengyu Huang , Tanya Goyal

What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approaches largely rely on binary pairwise comparisons, overlooking…

Information Retrieval · Computer Science 2026-04-20 Zhongyu Ouyang , Qianlong Wen , Chunhui Zhang , Yanfang Ye , Soroush Vosoughi

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Computation and Language · Computer Science 2025-10-27 Weibin Liao , Xu Chu , Yasha Wang

Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these…

Computation and Language · Computer Science 2023-12-12 Jian Hu , Li Tao , June Yang , Chandler Zhou

The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still rely heavily on substantial paired (labeled) feedback data,…

Machine Learning · Computer Science 2026-02-20 Seonggyun Lee , Sungjun Lim , Seojin Park , Soeun Cheon , Kyungwoo Song

This work studies the problem of large language model (LLM) unlearning, aiming to remove unwanted data influences (e.g., copyrighted or harmful content) while preserving model utility. Despite the increasing demand for unlearning, a…

Computation and Language · Computer Science 2025-10-21 Chongyu Fan , Jiancheng Liu , Licong Lin , Jinghan Jia , Ruiqi Zhang , Song Mei , Sijia Liu

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Minpeng Liao , Chengxi Li , Kai Fan

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

In recent years, the field of image generation has witnessed significant advancements, particularly in fine-tuning methods that align models with universal human preferences. This paper explores the critical role of preference data in the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Lingfan Zhang , Chen Liu , Chengming Xu , Kai Hu , Donghao Luo , Chengjie Wang , Yanwei Fu , Yuan Yao

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…

Machine Learning · Computer Science 2024-10-29 Sam Houliston , Alizée Pace , Alexander Immer , Gunnar Rätsch