English
Related papers

Related papers: $\phi$-DPO: Fairness Direct Preference Optimizatio…

200 papers

In the post-training of large language models (LLMs), Reinforcement Learning from Human Feedback (RLHF) is an effective approach to achieve generation aligned with human preferences. Direct Preference Optimization (DPO) allows for policy…

Machine Learning · Computer Science 2025-06-16 Motoki Omura , Yasuhiro Fujita , Toshiki Kataoka

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical…

Machine Learning · Computer Science 2025-07-08 Bo Wang , Qinyuan Cheng , Runyu Peng , Rong Bao , Peiji Li , Qipeng Guo , Linyang Li , Zhiyuan Zeng , Yunhua Zhou , Xipeng Qiu

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Computation and Language · Computer Science 2024-12-23 Shuo Xie , Fangzhi Zhu , Jiahui Wang , Lulu Wen , Wei Dai , Xiaowei Chen , Junxiong Zhu , Kai Zhou , Bo Zheng

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

Large Language Models (LLMs) rely on Human Preference Alignment (HPA) to ensure the generation of safe content. Due to the heavy cost associated with fine-tuning, fine-tuning-free methods have emerged, typically modifying LLM decoding with…

Computation and Language · Computer Science 2024-02-15 Feifan Song , Yuxuan Fan , Xin Zhang , Peiyi Wang , Houfeng Wang

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods. Existing works on model fusion focus primarily on supervised fine-tuning…

Machine Learning · Computer Science 2026-05-26 Yanggan Gu , Yuanyi Wang , Zhaoyi Yan , Yiming Zhang , Qi Zhou , Fei Wu , Hongxia Yang

Direct alignment algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcement learning with human feedback (RLHF). We show that DPO…

Machine Learning · Computer Science 2025-10-24 Aditya Gopalan , Sayak Ray Chowdhury , Debangshu Banerjee

Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is…

Computation and Language · Computer Science 2025-04-16 Aiwei Liu , Haoping Bai , Zhiyun Lu , Yanchao Sun , Xiang Kong , Simon Wang , Jiulong Shan , Albin Madappally Jose , Xiaojiang Liu , Lijie Wen , Philip S. Yu , Meng Cao

Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…

Computation and Language · Computer Science 2025-11-12 Rhitabrat Pokharel , Yufei Tao , Ameeta Agrawal

Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributionally. In this work,…

Machine Learning · Computer Science 2024-12-31 Hiroki Furuta , Kuang-Huei Lee , Shixiang Shane Gu , Yutaka Matsuo , Aleksandra Faust , Heiga Zen , Izzeddin Gur

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

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Computation and Language · Computer Science 2025-10-10 Jie Wu , Haoling Li , Xin Zhang , Xiao Liu , Yangyu Huang , Jianwen Luo , Yizhen Zhang , Zuchao Li , Ruihang Chu , Yujiu Yang , Scarlett Li

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

Machine Learning · Computer Science 2025-05-14 Teng Xiao , Zhen Ge , Sujay Sanghavi , Tian Wang , Julian Katz-Samuels , Marc Versage , Qingjun Cui , Trishul Chilimbi

Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to better distinguish between chosen (or preferred) and rejected…

Computation and Language · Computer Science 2025-06-09 Xiliang Yang , Feng Jiang , Qianen Zhang , Lei Zhao , Xiao Li

Large vision-language models (LVLMs) suffer from hallucination, resulting in misalignment between the output textual response and the input visual content. Recent research indicates that the over-reliance on the Large Language Model (LLM)…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Yuxi Xie , Guanzhen Li , Xiao Xu , Min-Yen Kan

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

Computation and Language · Computer Science 2025-07-30 Anas Mohamed , Azal Ahmad Khan , Xinran Wang , Ahmad Faraz Khan , Shuwen Ge , Saman Bahzad Khan , Ayaan Ahmad , Ali Anwar

Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become one of the most widely used algorithms for achieving this…

Machine Learning · Computer Science 2025-01-06 Rasul Tutnov , Antoine Grosnit , Haitham Bou-Ammar

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Minghao Fu , Guo-Hua Wang , Tianyu Cui , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang