English
Related papers

Related papers: Does Refusal Training in LLMs Generalize to the Pa…

200 papers

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

As the application of large language models continues to expand in various fields, it poses higher challenges to the effectiveness of identifying harmful content generation and guardrail mechanisms. This research aims to evaluate the…

Cryptography and Security · Computer Science 2025-03-21 Libo Wang

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Lin Li , Haoyan Guan , Jianing Qiu , Michael Spratling

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…

Artificial Intelligence · Computer Science 2026-04-03 Abinitha Gourabathina , Inkit Padhi , Manish Nagireddy , Subhajit Chaudhury , Prasanna Sattigeri

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safety training is that it algorithmically forbids the model…

Machine Learning · Computer Science 2024-02-09 Sophie Xhonneux , David Dobre , Jian Tang , Gauthier Gidel , Dhanya Sridhar

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Computation and Language · Computer Science 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

Large language models (LLMs) have become mainstream technology with their versatile use cases and impressive performance. Despite the countless out-of-the-box applications, LLMs are still not reliable. A lot of work is being done to improve…

Computation and Language · Computer Science 2023-06-13 Aisha Khatun , Daniel G. Brown

Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs). However, existing RLVR approaches train LMs based on their own on-policy responses and are constrained by the…

Machine Learning · Computer Science 2026-04-17 Chenming Tang , Hsiu-Yuan Huang , Weijie Liu , Clive Bai , Saiyong Yang , Yunfang Wu

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

Hate speech has become pervasive in today's digital age. Although there has been considerable research to detect hate speech or generate counter speech to combat hateful views, these approaches still cannot completely eliminate the…

Computation and Language · Computer Science 2023-10-24 Vibhor Agarwal , Yu Chen , Nishanth Sastry

Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However, a critical issue has been identified within this domain: the…

Computation and Language · Computer Science 2023-06-09 Chengguang Gan , Tatsunori Mori

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

GPT-3 and several other language models (LMs) can effectively address various natural language processing (NLP) tasks, including machine translation and text summarization. Recently, they have also been successfully employed in the business…

Artificial Intelligence · Computer Science 2023-04-17 Kiran Busch , Alexander Rochlitzer , Diana Sola , Henrik Leopold

Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using…

Cryptography and Security · Computer Science 2023-12-11 Zhuo Zhang , Guangyu Shen , Guanhong Tao , Siyuan Cheng , Xiangyu Zhang

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin

We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional methods, which require complex prompt engineering or white-box…

Machine Learning · Computer Science 2026-01-29 Piyush Jha , Arnav Arora , Vijay Ganesh

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

Computation and Language · Computer Science 2026-04-02 Tanay Gondil

Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance.…

Computation and Language · Computer Science 2023-06-07 Seonghyeon Ye , Doyoung Kim , Joel Jang , Joongbo Shin , Minjoon Seo

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

Computation and Language · Computer Science 2025-03-04 Shangding Gu , Alois Knoll , Ming Jin

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

Machine Learning · Computer Science 2023-10-30 Thomas Schmied , Markus Hofmarcher , Fabian Paischer , Razvan Pascanu , Sepp Hochreiter