English
Related papers

Related papers: Improving LLM Safety Alignment with Dual-Objective…

200 papers

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…

Computation and Language · Computer Science 2025-06-06 Wen Yang , Junhong Wu , Chen Wang , Chengqing Zong , Jiajun Zhang

Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Liming Lu , Xiang Gu , Shuchao Pang , Siyuan Liang , Haotian Zhu , Xiyu Zeng , Xu Zheng , Yongbin Zhou

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Computation and Language · Computer Science 2024-11-15 Somanshu Singla , Zhen Wang , Tianyang Liu , Abdullah Ashfaq , Zhiting Hu , Eric P. Xing

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

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

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Cryptography and Security · Computer Science 2025-06-05 Chen Xiong , Xiangyu Qi , Pin-Yu Chen , Tsung-Yi Ho

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

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

Most Video Large Language Models (Video-LLMs) adopt preference alignment techniques, e.g., DPO~\citep{rafailov2024dpo}, to optimize the reward margin between a winning response ($y_w$) and a losing response ($y_l$). However, the likelihood…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Xiaodong Wang , Jinfa Huang , Li Yuan , Peixi Peng

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Cryptography and Security · Computer Science 2026-01-05 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Chaohu Liu , Tianyi Gui , Yu Liu , Linli Xu

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Computation and Language · Computer Science 2025-03-04 Raghav Gupta , Ryan Sullivan , Yunxuan Li , Samrat Phatale , Abhinav Rastogi

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be…

Machine Learning · Computer Science 2025-02-06 Xuerui Su , Yue Wang , Jinhua Zhu , Mingyang Yi , Feng Xu , Zhiming Ma , Yuting Liu

Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental…

Machine Learning · Computer Science 2026-05-05 Haonan Zhang , Dongxia Wang , Yi Liu , Kexin Chen , Wenhai Wang

This research investigates the effectiveness of alignment techniques, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and a combined SFT+DPO approach on improving the safety and helpfulness of the OPT-350M language…

Computation and Language · Computer Science 2025-09-12 Piyush Pant

Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building on this observation, we model the safety mechanism as an unobserved confounder from a…

Computation and Language · Computer Science 2026-02-09 Yao Zhou , Zeen Song , Wenwen Qiang , Fengge Wu , Shuyi Zhou , Changwen Zheng , Hui Xiong

Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations about \texttt{DPO}. First, we show that \texttt{DPO} loss…