English
Related papers

Related papers: MetaSC: Test-Time Safety Specification Optimizatio…

200 papers

The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate retraining models,…

Computation and Language · Computer Science 2026-03-10 Sheikh Samit Muhaimin , Spyridon Mastorakis

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Machine Learning · Computer Science 2024-11-11 Andy Zhou , Bo Li , Haohan Wang

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000…

Artificial Intelligence · Computer Science 2026-01-09 Liang Shan , Kaicheng Shen , Wen Wu , Zhenyu Ying , Chaochao Lu , Yan Teng , Jingqi Huang , Guangze Ye , Guoqing Wang , Liang He

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Computation and Language · Computer Science 2025-10-17 Riccardo Cantini , Alessio Orsino , Massimo Ruggiero , Domenico Talia

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms…

Computation and Language · Computer Science 2025-07-28 Rithesh Murthy , Ming Zhu , Liangwei Yang , Jielin Qiu , Juntao Tan , Shelby Heinecke , Caiming Xiong , Silvio Savarese , Huan Wang

Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that this vulnerability stems from distributional discrepancies…

Computation and Language · Computer Science 2026-04-27 Jingyu Peng , Maolin Wang , Nan Wang , Jiatong Li , Yuchen Li , Yuyang Ye , Wanyu Wang , Pengyue Jia , Kai Zhang , Xiangyu Zhao

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Cryptography and Security · Computer Science 2026-03-17 Yu Pan , Wenlong Yu , Tiejun Wu , Xiaohu Ye , Qiannan Si , Guangquan Xu , Bin Wu

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Cryptography and Security · Computer Science 2026-05-06 Haoyu Zhang , Mohammad Zandsalimy , Shanu Sushmita

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Computation and Language · Computer Science 2025-03-31 Yazhou Zhang , Qimeng Liu , Qiuchi Li , Peng Zhang , Jing Qin

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Cryptography and Security · Computer Science 2025-02-10 Guobin Shen , Dongcheng Zhao , Yiting Dong , Xiang He , Yi Zeng

Accurate confidence calibration in Large Language Models (LLMs) is critical for safe use in high-stakes domains, where clear verbalized confidence enhances user trust. Traditional methods that mimic reference confidence expressions often…

Computation and Language · Computer Science 2025-10-29 Qing Zong , Jiayu Liu , Tianshi Zheng , Chunyang Li , Baixuan Xu , Haochen Shi , Weiqi Wang , Zhaowei Wang , Chunkit Chan , Yangqiu Song

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Cryptography and Security · Computer Science 2025-05-27 Haoyu Wang , Zeyu Qin , Yifei Zhao , Chao Du , Min Lin , Xueqian Wang , Tianyu Pang

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

Computation and Language · Computer Science 2024-03-08 Rui Wang , Hongru Wang , Fei Mi , Yi Chen , Boyang Xue , Kam-Fai Wong , Ruifeng Xu

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language,…

Computation and Language · Computer Science 2026-03-03 Xiaohe Bo , Rui Li , Zexu Sun , Quanyu Dai , Zeyu Zhang , Zihang Tian , Xu Chen , Zhenhua Dong

Large Language Models (LLMs) are increasingly deployed for task automation and content generation, yet their safety mechanisms remain vulnerable to circumvention through different jailbreaking techniques. In this paper, we introduce…

Cryptography and Security · Computer Science 2025-09-17 Johan Wahréus , Ahmed Hussain , Panos Papadimitratos