English
Related papers

Related papers: How Does DPO Reduce Toxicity? A Mechanistic Neuron…

200 papers

We introduce PEPO (Pessimistic Ensemble based Preference Optimization), a single-step Direct Preference Optimization (DPO)-like algorithm to mitigate the well-known over-optimization issue in preference learning without requiring the…

Machine Learning · Computer Science 2026-05-18 Adam Barla , Emanuele Nevali , Luca Viano , Volkan Cevher

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training…

Machine Learning · Computer Science 2026-05-11 Ning Liu , Chuanneng Sun , Kristina Klinkner , Shervin Malmasi

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning…

Machine Learning · Computer Science 2026-02-12 Kevin Rojas , Jiahe Lin , Kashif Rasul , Anderson Schneider , Yuriy Nevmyvaka , Molei Tao , Wei Deng

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods…

Artificial Intelligence · Computer Science 2025-07-30 Mengyang Li , Zhong Zhang

Direct Preference Optimization (DPO) has recently emerged as a simple and effective alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with user preferences. However, existing DPO…

Machine Learning · Computer Science 2025-10-10 Jason Bohne , Pawel Polak , David Rosenberg , Brian Bloniarz , Gary Kazantsev

Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibits poor out-of-distribution (OOD) generalisation. In this paper, we investigate whether…

Machine Learning · Computer Science 2026-05-27 Sandeep Kumar , Virginia Smith , Chhavi Yadav

Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this…

Machine Learning · Computer Science 2026-05-27 Jilong Liu , Yonghui Yang , Pengyang Shao , Wenjian Tao , Hao Zhan , Haokai Ma , Wei Qin , Richang Hong

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 alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Zonglin Lyu , Ming Li , Xinxin Liu , Chen Chen

Traditional RLHF-based LLM alignment methods explicitly maximize the expected rewards from a separate reward model. More recent supervised alignment methods like Direct Preference Optimization (DPO) circumvent this phase to avoid problems…

Machine Learning · Computer Science 2025-02-03 Abhijnan Nath , Changsoo Jung , Ethan Seefried , Nikhil Krishnaswamy

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference…

Machine Learning · Computer Science 2026-05-13 Zhengyuan Fan , Zhonghua Wu , Yuxuan Du , Qun Chen

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

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

Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…

Machine Learning · Computer Science 2026-01-30 Qian Wan , Ziao Xu , Luona Wei , Xiaoxuan Shen , Jianwen Sun

The proximal policy optimization (PPO) algorithm stands as one of the most prosperous methods in the field of reinforcement learning (RL). Despite its success, the theoretical understanding of PPO remains deficient. Specifically, it is…

Machine Learning · Computer Science 2023-06-09 Han Zhong , Tong Zhang

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen

State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model. To address this, we propose a novel method, Configurable Safety…

Computation and Language · Computer Science 2024-04-02 Victor Gallego
‹ Prev 1 8 9 10 Next ›