English
Related papers

Related papers: LLMs Can Unlearn Refusal with Only 1,000 Benign Sa…

200 papers

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user…

Artificial Intelligence · Computer Science 2026-01-21 Xiaorui Wu , Fei Li , Xiaofeng Mao , Xin Zhang , Li Zheng , Yuxiang Peng , Chong Teng , Donghong Ji , Zhuang Li

Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information, posing significant privacy risks. This study addresses the…

Computation and Language · Computer Science 2024-09-17 Zhenhua Liu , Tong Zhu , Chuanyuan Tan , Wenliang Chen

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we…

Cryptography and Security · Computer Science 2026-01-22 Luis Lazo , Hamed Jelodar , Roozbeh Razavi-Far

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. By targeting a single…

Computation and Language · Computer Science 2026-05-12 Hamid Kazemi , Atoosa Chegini , Maria Safi

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs' safety alignment…

Cryptography and Security · Computer Science 2025-11-27 Zhixin Xie , Xurui Song , Jun Luo

Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for…

Computation and Language · Computer Science 2025-08-27 Wenbo Zhang , Zihang Xu , Hengrui Cai

In this paper, we explore the potential of Large Language Models (LLMs) with assertions to mitigate imbalances in educational datasets. Traditional models often fall short in such contexts, particularly due to the complexity and nuanced…

Computers and Society · Computer Science 2024-07-03 Jeanne McClure , Machi Shimmei , Noboru Matsuda , Shiyan Jiang

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

Computation and Language · Computer Science 2025-03-26 Sravanti Addepalli , Yerram Varun , Arun Suggala , Karthikeyan Shanmugam , Prateek Jain

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Computation and Language · Computer Science 2022-12-20 Joel Jang , Dongkeun Yoon , Sohee Yang , Sungmin Cha , Moontae Lee , Lajanugen Logeswaran , Minjoon Seo

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Cryptography and Security · Computer Science 2025-11-25 Junbo Zhang , Ran Chen , Qianli Zhou , Xinyang Deng , Wen Jiang

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Computation and Language · Computer Science 2024-06-06 Jinghao Zhang , Yuting Liu , Qiang Liu , Shu Wu , Guibing Guo , Liang Wang

Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false…

Machine Learning · Computer Science 2026-03-17 Quan Liu , Han Zhou , Wenquan Wu , Hua Wu , Sen Su

Large Language Models (LLMs) are increasingly employed in various question-answering tasks. However, recent studies showcase that LLMs are susceptible to persuasion and could adopt counterfactual beliefs. We present a systematic evaluation…

Computation and Language · Computer Science 2026-03-20 Fan Huang , Haewoon Kwak , Jisun An

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks. Nonetheless, the resilience of LLMs…

Computation and Language · Computer Science 2024-10-04 Bin Wang , Chengwei Wei , Zhengyuan Liu , Geyu Lin , Nancy F. Chen

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Cryptography and Security · Computer Science 2025-07-16 Jérémie Dentan , Davide Buscaldi , Aymen Shabou , Sonia Vanier

The recent popularity of large language models (LLMs) has brought a significant impact to boundless fields, particularly through their open-ended ecosystem such as the APIs, open-sourced models, and plugins. However, with their widespread…

Machine Learning · Computer Science 2023-08-31 Wentao Ye , Mingfeng Ou , Tianyi Li , Yipeng chen , Xuetao Ma , Yifan Yanggong , Sai Wu , Jie Fu , Gang Chen , Haobo Wang , Junbo Zhao

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Computation and Language · Computer Science 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

Computation and Language · Computer Science 2025-11-03 Adel Khorramrouz , Sharon Levy