English
Related papers

Related papers: Lisa: Lazy Safety Alignment for Large Language Mod…

200 papers

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…

Artificial Intelligence · Computer Science 2026-01-01 Lijun Zhang , Lin Li , Wei Wei , Yajie Qi , Huizhong Song , Jun Wang , Yaodong Yang , Jiye Liang

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

Computation and Language · Computer Science 2025-11-11 Nicy Scaria , Silvester John Joseph Kennedy , Deepak Subramani

Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to…

Machine Learning · Computer Science 2025-05-20 Ning Lu , Shengcai Liu , Jiahao Wu , Weiyu Chen , Zhirui Zhang , Yew-Soon Ong , Qi Wang , Ke Tang

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Machine Learning · Computer Science 2023-11-07 Raphaël Millière

Large Language Models (LLMs) are often fine-tuned to adapt their general-purpose knowledge to specific tasks and domains such as cyber threat intelligence (CTI). Fine-tuning is mostly done through proprietary datasets that may contain…

Cryptography and Security · Computer Science 2026-03-13 Shashie Dilhara Batan Arachchige , Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Dinusha Vatsalan , Dali Kaafar

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

Machine Learning · Computer Science 2024-12-30 Rui Pan , Xiang Liu , Shizhe Diao , Renjie Pi , Jipeng Zhang , Chi Han , Tong Zhang

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Computation and Language · Computer Science 2026-04-13 Hadas Orgad , Boyi Wei , Kaden Zheng , Martin Wattenberg , Peter Henderson , Seraphina Goldfarb-Tarrant , Yonatan Belinkov

As the use of large language models (LLMs) increases within society, as does the risk of their misuse. Appropriate safeguards must be in place to ensure LLM outputs uphold the ethical standards of society, highlighting the positive role…

Computation and Language · Computer Science 2023-12-18 Veronica Chatrath , Oluwanifemi Bamgbose , Shaina Raza

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…

Cryptography and Security · Computer Science 2025-06-23 Biao Yi , Tiansheng Huang , Sishuo Chen , Tong Li , Zheli Liu , Zhixuan Chu , Yiming Li

Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed "aligned" can exhibit misaligned behavior after fine-tuning, such as…

Machine Learning · Computer Science 2026-02-02 Yavuz Bakman , Duygu Nur Yaldiz , Salman Avestimehr , Sai Praneeth Karimireddy

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Computation and Language · Computer Science 2025-11-10 Chung-En Sun , Xiaodong Liu , Weiwei Yang , Tsui-Wei Weng , Hao Cheng , Aidan San , Michel Galley , Jianfeng Gao

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…

Computation and Language · Computer Science 2025-08-13 Satya Swaroop Gudipudi , Sreeram Vipparla , Harpreet Singh , Shashwat Goel , Ponnurangam Kumaraguru

Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning large language models…

Computation and Language · Computer Science 2024-10-07 Dawei Zhu , Pinzhen Chen , Miaoran Zhang , Barry Haddow , Xiaoyu Shen , Dietrich Klakow

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Cryptography and Security · Computer Science 2025-01-22 David Williams-King , Linh Le , Adam Oberman , Yoshua Bengio

Recent research shows that Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- models lose their safety alignment ability after fine-tuning on a few harmful samples. For risk mitigation, a guardrail is typically…

Cryptography and Security · Computer Science 2025-01-30 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Ling Liu

Large Language Models (LLMs) exhibit a significant "embodiment gap", where their text-based representations fail to align with human sensorimotor experiences. This study systematically investigates whether and how task-specific fine-tuning…

Computation and Language · Computer Science 2026-03-05 Minghua Wu , Javier Conde , Pedro Reviriego , Marc Brysbaert
‹ Prev 1 8 9 10 Next ›