English
Related papers

Related papers: Efficient Switchable Safety Control in LLMs via Ma…

200 papers

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Machine Learning · Computer Science 2026-02-10 Kaustubh Ponkshe , Shaan Shah , Raghav Singhal , Praneeth Vepakomma

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

Computation and Language · Computer Science 2025-10-24 Jianhui Chen , Xiaozhi Wang , Zijun Yao , Yushi Bai , Lei Hou , Juanzi Li

Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility of model outputs and mitigating their potential for harm is a complex and persistent challenge.…

Machine Learning · Computer Science 2025-10-07 Kartik Pandit , Sourav Ganguly , Arnesh Banerjee , Shaahin Angizi , Arnob Ghosh

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the safety filter, designed…

Systems and Control · Electrical Eng. & Systems 2026-03-31 Yuya Miyaoka , Masaki Inoue

Ensuring robot safety in complex environments is a difficult task due to actuation limits, such as torque bounds. This paper presents a safety-critical control framework that leverages learning-based switching between multiple backup…

Robotics · Computer Science 2024-03-08 Neil C. Janwani , Ersin Daş , Thomas Touma , Skylar X. Wei , Tamas G. Molnar , Joel W. Burdick

Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks. Existing safety techniques -- including external…

Artificial Intelligence · Computer Science 2025-10-03 Yuhao Sun , Zhuoer Xu , Shiwen Cui , Kun Yang , Lingyun Yu , Yongdong Zhang , Hongtao Xie

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and…

Computation and Language · Computer Science 2025-03-13 Bilgehan Sel , Dingcheng Li , Phillip Wallis , Vaishakh Keshava , Ming Jin , Siddhartha Reddy Jonnalagadda

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…

Cryptography and Security · Computer Science 2026-01-16 Hao Wang , Yanting Wang , Hao Li , Rui Li , Lei Sha

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du

Given the societal impact of unsafe content generated by large language models (LLMs), ensuring that LLM services comply with safety standards is a crucial concern for LLM service providers. Common content moderation methods are limited by…

Computation and Language · Computer Science 2024-09-06 Jialin Wu , Jiangyi Deng , Shengyuan Pang , Yanjiao Chen , Jiayang Xu , Xinfeng Li , Wenyuan Xu

Merely pursuing performance may adversely affect the safety, while a conservative policy for safe exploration will degrade the performance. How to balance the safety and performance in learning-based control problems is an interesting yet…

Systems and Control · Electrical Eng. & Systems 2025-01-28 Xinyang Wang , Hongwei Zhang , Shimin Wang , Wei Xiao , Martin Guay

This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the CBF safety filter to the…

Computation and Language · Computer Science 2026-03-31 Yuya Miyaoka , Masaki Inoue

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Machine Learning · Computer Science 2025-10-10 Huahui Yi , Kun Wang , Qiankun Li , Miao Yu , Liang Lin , Gongli Xi , Hao Wu , Xuming Hu , Kang Li , Yang Liu

Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant…

Computation and Language · Computer Science 2026-03-03 Yanping Li , Zhening Liu , Zijian Li , Zehong Lin , Jun Zhang

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…

Artificial Intelligence · Computer Science 2023-10-20 Josef Dai , Xuehai Pan , Ruiyang Sun , Jiaming Ji , Xinbo Xu , Mickel Liu , Yizhou Wang , Yaodong Yang

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Artificial Intelligence · Computer Science 2026-05-12 Yi Zhang , Yuxin Chen , Leheng Sheng , Dongcheng Zhang , Chaochao Lu , Xiang Wang , An Zhang