English
Related papers

Related papers: Linearly Decoding Refused Knowledge in Aligned Lan…

200 papers

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…

Computation and Language · Computer Science 2024-08-20 Kexin Chen , Yi Liu , Dongxia Wang , Jiaying Chen , Wenhai Wang

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Computation and Language · Computer Science 2025-05-30 Wei Jie Yeo , Nirmalendu Prakash , Clement Neo , Roy Ka-Wei Lee , Erik Cambria , Ranjan Satapathy

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potentially harmful content.…

Computation and Language · Computer Science 2024-04-09 Peng Ding , Jun Kuang , Dan Ma , Xuezhi Cao , Yunsen Xian , Jiajun Chen , Shujian Huang

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…

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

Computation and Language · Computer Science 2026-02-10 Thilo Hagendorff , Erik Derner , Nuria Oliver

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Computation and Language · Computer Science 2025-05-13 Brian R. Y. Huang , Maximilian Li , Leonard Tang

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…

Artificial Intelligence · Computer Science 2026-02-03 Vikram Natarajan , Devina Jain , Shivam Arora , Satvik Golechha , Joseph Bloom

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…

Computation and Language · Computer Science 2024-06-10 Hanning Zhang , Shizhe Diao , Yong Lin , Yi R. Fung , Qing Lian , Xingyao Wang , Yangyi Chen , Heng Ji , Tong Zhang

Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs' inherent knowledge and the possible remedies. We start by…

Computation and Language · Computer Science 2024-02-19 Duc N. M Hoang , Minsik Cho , Thomas Merth , Mohammad Rastegari , Zhangyang Wang

Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they remain vulnerable to jailbreak attacks, which exploit weaknesses in their safety alignment to…

Cryptography and Security · Computer Science 2025-08-29 Wenzhuo Xu , Zhipeng Wei , Xiongtao Sun , Zonghao Ying , Deyue Zhang , Dongdong Yang , Xiangzheng Zhang , Quanchen Zou

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Software Engineering · Computer Science 2026-04-21 Claudio Spiess , Prem Devanbu , Earl T. Barr

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Large language models (LLMs) have shown success in many natural language processing tasks. Despite rigorous safety alignment processes, supposedly safety-aligned LLMs like Llama 2 and Claude 2 are still susceptible to jailbreaks, leading to…

Computation and Language · Computer Science 2024-05-15 Ziyang Zhang , Qizhen Zhang , Jakob Foerster

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…

Computation and Language · Computer Science 2025-09-30 Hua Tang , Lingyong Yan , Yukun Zhao , Shuaiqiang Wang , Jizhou Huang , Dawei Yin

We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to provide prompts and upvote / downvote feedback on LM outputs.…

Computation and Language · Computer Science 2026-04-21 Almog Hilel , Riddhi Bhagwat , Idan Shenfeld , Jacob Andreas , Leshem Choshen

Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking."…

Computation and Language · Computer Science 2024-02-27 Zhenhua Wang , Wei Xie , Baosheng Wang , Enze Wang , Zhiwen Gui , Shuoyoucheng Ma , Kai Chen

Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabilities, behavioral profile, and internal failure mode. We study behavioral and mechanistic…

Cryptography and Security · Computer Science 2026-04-21 Md Rysul Kabir , Zoran Tiganj
‹ Prev 1 8 9 10 Next ›