English
Related papers

Related papers: BSO: Safety Alignment Is Density Ratio Matching

200 papers

Direct Preference Optimization (DPO) is a simple and efficient framework that has attracted substantial attention. However, it often struggles to meet its primary objectives -- increasing the generation probability of chosen responses while…

Artificial Intelligence · Computer Science 2025-06-17 Jay Hyeon Cho , JunHyeok Oh , Myunsoo Kim , Byung-Jun Lee

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose…

Computation and Language · Computer Science 2026-05-12 Mengyi Deng , Zhiwei Li , Xin Li , Tingyu Zhu , Yulan Yuan , Zhijiang Guo , Wei Wang

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Machine Learning · Computer Science 2025-02-04 Ching-Chia Kao , Chia-Mu Yu , Chun-Shien Lu , Chu-Song Chen

Bayesian optimization has attracted huge attention from diverse research areas in science and engineering, since it is capable of efficiently finding a global optimum of an expensive-to-evaluate black-box function. In general, a…

Machine Learning · Computer Science 2025-07-29 Jungtaek Kim

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

Artificial Intelligence · Computer Science 2024-06-11 Biqing Qi , Pengfei Li , Fangyuan Li , Junqi Gao , Kaiyan Zhang , Bowen Zhou

Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency…

Robotics · Computer Science 2023-07-31 Haotian Xu , Shengjie Wang , Zhaolei Wang , Yunzhe Zhang , Qing Zhuo , Yang Gao , Tao Zhang

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Machine Learning · Computer Science 2025-01-28 Nirav Diwan , Tolga Ergen , Dongsub Shim , Honglak Lee

Sample efficiency is one of the key factors when applying policy search to real-world problems. In recent years, Bayesian Optimization (BO) has become prominent in the field of robotics due to its sample efficiency and little prior…

Robotics · Computer Science 2020-11-19 Lukas P. Fröhlich , Melanie N. Zeilinger , Edgar D. Klenske

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences. In this…

Machine Learning · Computer Science 2025-04-07 Hanping Zhang , Yuhong Guo

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

Machine Learning · Computer Science 2026-05-21 Shengfan Cao , Francesco Borrelli , Eunhyek Joa

Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise…

Machine Learning · Computer Science 2024-10-03 Weiye Zhao , Feihan Li , Yifan Sun , Yujie Wang , Rui Chen , Tianhao Wei , Changliu Liu

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

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the \emph{alignment tax}. We study this trade-off through the…

Machine Learning · Computer Science 2026-05-13 Guanglong Sun , Siyuan Zhang , Liyuan Wang , Jun Zhu , Hang Su , Yi Zhong

Bayesian optimization (BO) is a powerful approach to sample-efficient optimization of black-box objective functions. However, the application of BO to areas such as recommendation systems often requires taking the interpretability and…

Machine Learning · Computer Science 2023-03-06 Sulin Liu , Qing Feng , David Eriksson , Benjamin Letham , Eytan Bakshy

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

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the…

Machine Learning · Computer Science 2025-03-25 Juntao Dai , Taiye Chen , Yaodong Yang , Qian Zheng , Gang Pan

Black-box zero-th order optimization is a central primitive for applications in fields as diverse as finance, physics, and engineering. In a common formulation of this problem, a designer sequentially attempts candidate solutions, receiving…

Machine Learning · Computer Science 2024-07-08 Yunchuan Zhang , Sangwoo Park , Osvaldo Simeone

Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many…

Machine Learning · Statistics 2023-11-27 Shin Matsushima , Hyokun Yun , Xinhua Zhang , S. V. N. Vishwanathan

Most 3D object generators prioritize aesthetic quality, often neglecting the physical constraints necessary for practical applications. One such constraint is that a 3D object should be self-supporting, i.e., remain balanced under gravity.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Ruining Li , Chuanxia Zheng , Christian Rupprecht , Andrea Vedaldi
‹ Prev 1 4 5 6 7 8 10 Next ›