English
Related papers

Related papers: Safe RLHF-V: Safe Reinforcement Learning from Mult…

200 papers

Ensuring Large Language Models (LLMs) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learning from Human Feedback (RLHF), rely on centralized data…

Machine Learning · Computer Science 2025-03-14 Mahmoud Srewa , Tianyu Zhao , Salma Elmalaki

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

Cryptography and Security · Computer Science 2025-06-03 Youze Wang , Wenbo Hu , Yinpeng Dong , Jing Liu , Hanwang Zhang , Richang Hong

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Machine Learning · Computer Science 2026-01-07 Jiawen Zhang , Lipeng He , Kejia Chen , Jian Lou , Jian Liu , Xiaohu Yang , Ruoxi Jia

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Shen Li , Liuyi Yao , Wujia Niu , Lan Zhang , Yaliang Li

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Computation and Language · Computer Science 2025-12-22 Kangwei Liu , Mengru Wang , Yujie Luo , Lin Yuan , Mengshu Sun , Lei Liang , Zhiqiang Zhang , Jun Zhou , Bryan Hooi , Shumin Deng

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges,…

Machine Learning · Computer Science 2026-04-09 Peigui Qi , Kunsheng Tang , Yanpu Yu , Jialin Wu , Yide Song , Wenbo Zhou , Zhicong Huang , Cheng Hong , Weiming Zhang , Nenghai Yu

Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more helpful and harmless responses. Reward models are trained as…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Computation and Language · Computer Science 2024-10-15 Minjun Zhu , Linyi Yang , Yifan Wei , Ningyu Zhang , Yue Zhang

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

Computers and Society · Computer Science 2023-11-29 Nathan Lambert , Thomas Krendl Gilbert , Tom Zick

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of cultural and legal standards across the world. To…

Computation and Language · Computer Science 2024-12-10 Da Yin , Haoyi Qiu , Kung-Hsiang Huang , Kai-Wei Chang , Nanyun Peng

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL.…

Artificial Intelligence · Computer Science 2025-05-19 Yue Liu , Shengfang Zhai , Mingzhe Du , Yulin Chen , Tri Cao , Hongcheng Gao , Cheng Wang , Xinfeng Li , Kun Wang , Junfeng Fang , Jiaheng Zhang , Bryan Hooi

As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Lei Li , Zhihui Xie , Mukai Li , Shunian Chen , Peiyi Wang , Liang Chen , Yazheng Yang , Benyou Wang , Lingpeng Kong , Qi Liu

Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite the promising potential of RLHF, how to protect user…

Machine Learning · Computer Science 2025-02-26 Jiaming Zhang , Mingxi Lei , Meng Ding , Mengdi Li , Zihang Xiang , Difei Xu , Jinhui Xu , Di Wang

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

Machine Learning · Statistics 2026-02-11 Kai Ye , Hongyi Zhou , Jin Zhu , Francesco Quinzan , Chengchun Shi

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective…

Machine Learning · Computer Science 2024-12-10 Subhojyoti Mukherjee , Anusha Lalitha , Sailik Sengupta , Aniket Deshmukh , Branislav Kveton

Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI…

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

Computation and Language · Computer Science 2025-07-18 Wenliang Shan , Michael Fu , Rui Yang , Chakkrit Tantithamthavorn

RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction following tasks; however, it exhibits insufficient compliance…

Artificial Intelligence · Computer Science 2025-05-20 Ruopei Sun , Jianfeng Cai , Jinhua Zhu , Kangwen Zhao , Dongyun Xue , Wengang Zhou , Li Li , Houqiang Li