English
Related papers

Related papers: Lightweight Safety Guardrails Using Fine-tuned BER…

200 papers

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Cryptography and Security · Computer Science 2024-06-26 Yi Zeng , Weiyu Sun , Tran Ngoc Huynh , Dawn Song , Bo Li , Ruoxi Jia

Large Language Models (LLMs) such as Gemma-2B have shown strong performance in various natural language processing tasks. However, general-purpose models often lack the domain expertise required for cybersecurity applications. This work…

Cryptography and Security · Computer Science 2026-01-13 Vasanth Iyer , Leonardo Bobadilla , S. S. Iyengar

Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance. However, existing PEFT methods are still limited by the growing number of…

Computation and Language · Computer Science 2024-02-20 Yifan Yang , Jiajun Zhou , Ngai Wong , Zheng Zhang

As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained, interpretable, and adaptable risk assessment. However,…

The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. While large language models (LLMs) are effective, their high computational cost and latency…

Computation and Language · Computer Science 2026-04-09 Shutong Zhang , Dylan Zhou , Yinxiao Liu , Yang Yang , Huiwen Luo , Wenfei Zou

The pervasiveness of large language models (LLMs) in enterprise settings has also brought forth a significant amount of risks associated with their usage. Guardrails technologies aim to mitigate this risk by filtering LLMs' input/output…

Computation and Language · Computer Science 2025-08-27 Kellen Tan Cheng , Anna Lisa Gentile , Chad DeLuca , Guang-Jie Ren

The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim…

Cryptography and Security · Computer Science 2025-08-22 Itay Hazan , Idan Habler , Ron Bitton , Itsik Mantin

Ensuring content safety in large language models (LLMs) is essential for their deployment in real-world applications. However, existing safety guardrails are predominantly tailored for high-resource languages, leaving a significant portion…

Computation and Language · Computer Science 2026-03-31 Lavish Bansal , Naman Mishra

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Artificial Intelligence · Computer Science 2025-08-26 Chongwen Zhao , Zhihao Dou , Kaizhu Huang

As Industry 4.0 transforms the food industry, the role of software in achieving compliance with food-safety regulations is becoming increasingly critical. Food-safety regulations, like those in many legal domains, have largely been…

Software Engineering · Computer Science 2025-01-27 Shabnam Hassani , Mehrdad Sabetzadeh , Daniel Amyot

Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…

Computation and Language · Computer Science 2024-04-19 Nicholas Harris , Anand Butani , Syed Hashmy

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…

Machine Learning · Computer Science 2024-11-01 ShengYun Peng , Pin-Yu Chen , Matthew Hull , Duen Horng Chau

Slot labelling is an essential component of any dialogue system, aiming to find important arguments in every user turn. Common approaches involve large pre-trained language models (PLMs) like BERT or RoBERTa, but they face challenges such…

Computation and Language · Computer Science 2024-01-22 Vladimir Vlasov

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Truyen Tran

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Machine Learning · Computer Science 2026-03-03 Yuhui Wang , Rongyi Zhu , Ting Wang

Fine-tuning a pre-trained model, such as Bidirectional Encoder Representations from Transformers (BERT), has been proven to be an effective method for solving many natural language processing (NLP) tasks. However, due to the large number of…

Computation and Language · Computer Science 2024-04-01 Taha ValizadehAslani , Hualou Liang

Models based on BERT have been extremely successful in solving a variety of natural language processing (NLP) tasks. Unfortunately, many of these large models require a great deal of computational resources and/or time for pre-training and…

Computation and Language · Computer Science 2022-02-28 Sharath Nittur Sridhar , Anthony Sarah , Sairam Sundaresan

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with…

Machine Learning · Computer Science 2025-11-10 Haibo Jin , Ruoxi Chen , Peiyan Zhang , Andy Zhou , Haohan Wang

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

Artificial Intelligence · Computer Science 2024-06-17 Wei Zhao , Zhe Li , Yige Li , Ye Zhang , Jun Sun

Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local…

Artificial Intelligence · Computer Science 2025-08-07 Yanjie Dong , Haijun Zhang , Chengming Li , Song Guo , Victor C. M. Leung , Xiping Hu