English
Related papers

Related papers: Cat-DPO: Category-Adaptive Safety Alignment

200 papers

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

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Machine Learning · Computer Science 2024-05-29 Xize Liang , Chao Chen , Shuang Qiu , Jie Wang , Yue Wu , Zhihang Fu , Zhihao Shi , Feng Wu , Jieping Ye

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

Machine Learning · Computer Science 2026-05-18 Yue Wang , Qizhou Wang , Zizhuo Zhang , Gang Niu , Bo Han , Masashi Sugiyama

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

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

Computation and Language · Computer Science 2025-02-19 Amir Saeidi , Shivanshu Verma , Aswin RRV , Kashif Rasul , Chitta Baral

Direct Alignment Algorithms (DAAs), such as Direct Preference Optimisation (DPO) and Identity Preference Optimisation (IPO), have emerged as alternatives to online Reinforcement Learning from Human Feedback (RLHF) algorithms such as…

Computation and Language · Computer Science 2024-10-21 Zhengyan Shi , Sander Land , Acyr Locatelli , Matthieu Geist , Max Bartolo

Direct Preference Optimization (DPO) has shown strong potential for mitigating hallucinations in Multimodal Large Language Models (MLLMs). However, existing multimodal DPO approaches often suffer from overfitting due to the difficulty…

Artificial Intelligence · Computer Science 2026-01-05 Longtian Qiu , Shan Ning , Chuyu Zhang , Jiaxuan Sun , Xuming He

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Computation and Language · Computer Science 2025-06-05 Honggen Zhang , Xufeng Zhao , Igor Molybog , June Zhang

Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline…

Machine Learning · Computer Science 2024-10-23 Wenda Xu , Jiachen Li , William Yang Wang , Lei Li

Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within…

Computation and Language · Computer Science 2025-07-11 Zhijin Dong

Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has emerged as a potent…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Dain Kim , Jiwoo Lee , Jaehoon Yun , Yong Hoe Koo , Qingyu Chen , Hyunjae Kim , Jaewoo Kang

The rapid advancement of large language models (LLMs) has facilitated their transformation into conversational chatbots that can grasp contextual nuances and generate pertinent sentences, closely mirroring human values through advanced…

Computation and Language · Computer Science 2024-07-19 Janghwan Lee , Seongmin Park , Sukjin Hong , Minsoo Kim , Du-Seong Chang , Jungwook Choi

The ability of LLMs to represent diverse perspectives is critical as they increasingly impact society. However, recent studies reveal that alignment algorithms such as RLHF and DPO significantly reduce the diversity of LLM outputs. Not only…

Computation and Language · Computer Science 2025-11-13 Stewart Slocum , Asher Parker-Sartori , Dylan Hadfield-Menell

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Machine Learning · Computer Science 2026-02-11 Yuxuan Tang , Yifan Feng

Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradley-Terry (BT) model may limit its full…

Artificial Intelligence · Computer Science 2026-02-11 Masanari Oi , Mahiro Ukai , Masahiro Kaneko , Naoaki Okazaki , Nakamasa Inoue

Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference…

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

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

Machine Learning · Computer Science 2025-09-17 Denis Janiak , Julia Moska , Dawid Motyka , Karolina Seweryn , Paweł Walkowiak , Bartosz Żuk , Arkadiusz Janz

As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori Preference…

Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment…

Machine Learning · Computer Science 2026-03-09 Xiangwen Wang , Yibo Jacky Zhang , Zhoujie Ding , Katherine Tsai , Haolun Wu , Sanmi Koyejo