English
Related papers

Related papers: MOSAIC: Composable Safety Alignment with Modular C…

200 papers

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Cryptography and Security · Computer Science 2026-05-19 Tim Beyer , Sophie Xhonneux , Simon Geisler , Gauthier Gidel , Leo Schwinn , Stephan Günnemann

Instruction tuning has empowered large language models (LLMs) to achieve remarkable performance, yet its success heavily depends on the availability of large-scale, high-quality instruction-response pairs. To meet this demand, various…

Computation and Language · Computer Science 2025-12-19 Fanyi Yang , Jianfeng Liu , Xin Zhang , Haoyu Liu , Xixin Cao , Yuefeng Zhan , Hao Sun , Weiwei Deng , Feng Sun , Qi Zhang

Autonomous systems are increasingly deployed in real-world environments, where they must achieve high performance while maintaining safety under state and input constraints. Although Model Predictive Control (MPC) provides a principled…

Robotics · Computer Science 2026-04-28 Hao Wang , Nam Nguyen , Armand Jordana , Ludovic Righetti , Somil Bansal

Agents controlled by the output of reinforcement learning (RL) algorithms often transition to unsafe states, particularly in uncertain and partially observable environments. Partially observable Markov decision processes (POMDPs) provide a…

Systems and Control · Electrical Eng. & Systems 2025-09-16 Steven Carr , Georgios Bakirtzis , Ufuk Topcu

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

Computation and Language · Computer Science 2026-01-06 Dianyun Wang , Qingsen Ma , Yuhu Shang , Zhifeng Lu , Zhenbo Xu , Lechen Ning , Huijia Wu , Zhaofeng He

Visual tokens consume substantial computational resources in multi-modal large models (MLLMs), significantly compromising their efficiency. Recent works have attempted to improve efficiency by compressing visual tokens during training,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Zichen Wen , Shaobo Wang , Yufa Zhou , Junyuan Zhang , Qintong Zhang , Yifeng Gao , Zhaorun Chen , Bin Wang , Weijia Li , Conghui He , Linfeng Zhang

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a…

Computation and Language · Computer Science 2026-02-09 Jianfeng Si , Lin Sun , Weihong Lin , Xiangzheng Zhang

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Machine Learning · Computer Science 2025-11-18 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Cryptography and Security · Computer Science 2025-11-11 Haonan Shi , Guoli Wang , Tu Ouyang , An Wang

Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Output (I/O) test cases. However, this does not work for scientific workflows, where I/O…

Software Engineering · Computer Science 2026-04-28 Siddeshwar Raghavan , Tanwi Mallick

Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak attacks in low-resource languages. Current safety alignment…

Machine Learning · Computer Science 2026-05-11 Ruiyang Qin , Qingzhuo Wang , Dongrui Liu , Qiang Li , Zhihua Wei , Wen Shen

We consider the problem of safely coordinating ensembles of identical autonomous agents to conduct complex missions with conflicting safety requirements and under noisy control inputs. Using non-smooth control barrier functions (CBFs) and…

Systems and Control · Electrical Eng. & Systems 2024-03-29 Clinton Enwerem , John S. Baras

Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted prompts bypass safety mechanisms. Understanding the causal factors behind such…

Cryptography and Security · Computer Science 2025-12-05 Wei Zhao , Zhe Li , Jun Sun

Automatic Modulation Classification (AMC) is critical for efficient spectrum management and robust wireless communications. However, AMC remains challenging due to the complex interplay of signal interference and noise. In this work, we…

Machine Learning · Computer Science 2025-10-28 Mohammad Rostami , Atik Faysal , Reihaneh Gh. Roshan , Huaxia Wang , Nikhil Muralidhar , Yu-Dong Yao

We introduce a modular prompting framework that supports safer and more adaptive use of large language models (LLMs) across dynamic, user-centered tasks. Grounded in human learning theory, particularly the Zone of Proximal Development…

Artificial Intelligence · Computer Science 2025-08-12 Vanessa Figueiredo

Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during…

Robotics · Computer Science 2023-11-29 Ziyi Yang , Shreyas S. Raman , Ankit Shah , Stefanie Tellex

Large Language Models (LLMs) have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts…

Cryptography and Security · Computer Science 2025-10-22 Hanbin Hong , Shuya Feng , Nima Naderloui , Shenao Yan , Jingyu Zhang , Biying Liu , Ali Arastehfard , Heqing Huang , Yuan Hong

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Cryptography and Security · Computer Science 2024-12-25 Caishuang Huang , Wanxu Zhao , Rui Zheng , Huijie Lv , Wenyu Zhan , Shihan Dou , Sixian Li , Xiao Wang , Enyu Zhou , Junjie Ye , Yuming Yang , Tao Gui , Qi Zhang , Xuanjing Huang

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic…

Machine Learning · Computer Science 2026-04-24 Junxiao Yang , Haoran Liu , Jinzhe Tu , Jiale Cheng , Zhexin Zhang , Shiyao Cui , Jiaqi Weng , Jialing Tao , Hui Xue , Hongning Wang , Han Qiu , Minlie Huang

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun
‹ Prev 1 4 5 6 7 8 10 Next ›