English
Related papers

Related papers: Make Them Spill the Beans! Coercive Knowledge Extr…

200 papers

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Cryptography and Security · Computer Science 2026-04-02 Anubhab Sahu , Diptisha Samanta , Reza Soosahabi

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

Cryptography and Security · Computer Science 2025-06-17 Advait Yadav , Haibo Jin , Man Luo , Jun Zhuang , Haohan Wang

Evaluating generative models, such as large language models (LLMs), commonly involves question-answering tasks where the final answer is selected based on probability of answer choices. On the other hand, for models requiring reasoning, the…

Computation and Language · Computer Science 2025-10-17 Hwiyeol Jo , Joosung Lee , Jaehone Lee , Sang-Woo Lee , Joonsuk Park , Kang Min Yoo

The utility of Large Language Models (LLMs) in analytical tasks is rooted in their vast pre-trained knowledge, which allows them to interpret ambiguous inputs and infer missing information. However, this same capability introduces a…

Artificial Intelligence · Computer Science 2026-04-21 Humam Kourani , Anton Antonov , Alessandro Berti , Wil M. P. van der Aalst

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Computation and Language · Computer Science 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che

The integration of large language models (LLMs) and search engines represents a significant evolution in knowledge acquisition methodologies. However, determining the knowledge that an LLM already possesses and the knowledge that requires…

Computation and Language · Computer Science 2024-05-31 Jiejun Tan , Zhicheng Dou , Yutao Zhu , Peidong Guo , Kun Fang , Ji-Rong Wen

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Cryptography and Security · Computer Science 2026-04-10 Yulin Chen , Haoran Li , Yuan Sui , Yue Liu , Yufei He , Xiaoling Bai , Chi Fei , Yabo Li , Haozhe Ma , Yangqiu Song , Bryan Hooi

Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the…

Machine Learning · Computer Science 2025-12-24 Manas Joglekar , Jeremy Chen , Gabriel Wu , Jason Yosinski , Jasmine Wang , Boaz Barak , Amelia Glaese

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the…

Machine Learning · Computer Science 2024-03-01 Xue Yan , Yan Song , Xinyu Cui , Filippos Christianos , Haifeng Zhang , David Henry Mguni , Jun Wang

The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However,…

Computation and Language · Computer Science 2024-07-24 Min Zhang , Jianfeng He , Taoran Ji , Chang-Tien Lu

In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…

Computation and Language · Computer Science 2024-10-15 Yifan Luo , Zhennan Zhou , Meitan Wang , Bin Dong

Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff test data may reflect memorization rather than reasoning,…

Computation and Language · Computer Science 2025-10-16 Xin Gao , Ruiyi Zhang , Daniel Du , Saurabh Mahindre , Sai Ashish Somayajula , Pengtao Xie

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…

Cryptography and Security · Computer Science 2024-05-31 Patrick Levi , Christoph P. Neumann

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

Computation and Language · Computer Science 2024-07-23 Xiao Liu , Liangzhi Li , Tong Xiang , Fuying Ye , Lu Wei , Wangyue Li , Noa Garcia

Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4's law evaluation raise questions concerning their performance in real-world legal…

Computation and Language · Computer Science 2023-10-19 Ruihao Shui , Yixin Cao , Xiang Wang , Tat-Seng Chua

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

Cryptography and Security · Computer Science 2025-05-21 Zhexin Zhang , Junxiao Yang , Yida Lu , Pei Ke , Shiyao Cui , Chujie Zheng , Hongning Wang , Minlie Huang

The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where the LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is more…

Computation and Language · Computer Science 2025-02-10 Yusuke Ide , Yuto Nishida , Justin Vasselli , Miyu Oba , Yusuke Sakai , Hidetaka Kamigaito , Taro Watanabe

Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails. Previous attempts to exploit these vulnerabilities often rely on high-cost…

Machine Learning · Computer Science 2024-12-02 Xuan Li , Zhanke Zhou , Jianing Zhu , Jiangchao Yao , Tongliang Liu , Bo Han

One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training…

Computation and Language · Computer Science 2024-12-24 Johannes Treutlein , Dami Choi , Jan Betley , Samuel Marks , Cem Anil , Roger Grosse , Owain Evans