English
Related papers

Related papers: Sysformer: Safeguarding Frozen Large Language Mode…

200 papers

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…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and…

Cryptography and Security · Computer Science 2025-02-25 Hongfu Liu , Hengguan Huang , Xiangming Gu , Hao Wang , Ye Wang

Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or ``prompting,'' practitioners are able to use LLMs to quickly get a response for an…

Computation and Language · Computer Science 2024-04-03 Abel Salinas , Fred Morstatter

Before adopting a new large language model (LLM) architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully…

Cryptography and Security · Computer Science 2025-10-08 Mary Llewellyn , Annie Gray , Josh Collyer , Michael Harries

Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies…

Computation and Language · Computer Science 2024-06-18 Zhenyu Zhang , Bingguang Hao , Jinpeng Li , Zekai Zhang , Dongyan Zhao

Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations to…

Machine Learning · Computer Science 2026-02-26 Yuxin Xiao , Sana Tonekaboni , Walter Gerych , Vinith Suriyakumar , Marzyeh Ghassemi

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling…

Information Retrieval · Computer Science 2025-07-21 Genki Kusano , Kosuke Akimoto , Kunihiro Takeoka

Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and…

Computation and Language · Computer Science 2025-10-13 Yumin Choi , Jinheon Baek , Sung Ju Hwang

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to…

Computation and Language · Computer Science 2024-05-16 Ning Lu , Shengcai Liu , Rui He , Qi Wang , Yew-Soon Ong , Ke Tang

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

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM…

Cryptography and Security · Computer Science 2026-03-26 Zheng Zhang , Peilin Zhao , Deheng Ye , Hao Wang

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Machine Learning · Computer Science 2025-11-18 Gil Goren , Shahar Katz , Lior Wolf

User prompts to large language models (LLMs) are often ambiguous or under-specified, and subtle contextual cues shaped by user intentions, prior knowledge, and risk factors strongly influence what constitutes an appropriate response.…

Machine Learning · Computer Science 2025-12-16 Minseon Kim , Lucas Caccia , Zhengyan Shi , Matheus Pereira , Marc-Alexandre Côté , Xingdi Yuan , Alessandro Sordoni

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the…

Cryptography and Security · Computer Science 2025-03-03 Weiran Lin , Anna Gerchanovsky , Omer Akgul , Lujo Bauer , Matt Fredrikson , Zifan Wang