English
Related papers

Related papers: Efficiency vs. Alignment: Investigating Safety and…

200 papers

AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. For example, before Meta released Llama 2-Chat - a collection of instruction fine-tuned large language models - they invested heavily in safety…

Machine Learning · Computer Science 2024-05-24 Simon Lermen , Charlie Rogers-Smith , Jeffrey Ladish

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Computation and Language · Computer Science 2025-05-27 Di Wu , Xin Lu , Yanyan Zhao , Bing Qin

Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fine-tuning techniques improve role adaptability but may…

Computation and Language · Computer Science 2025-05-28 Weixiang Zhao , Yulin Hu , Yang Deng , Jiahe Guo , Xingyu Sui , Xinyang Han , An Zhang , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

This review surveys the rapid evolution of Meta AI's LLaMA (Large Language Model Meta AI) series - from LLaMA 1 through LLaMA 4 and the specialized parameter-efficient fine-tuning (PEFT) methods developed for these models. We first describe…

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong

Low Rank Adaptation (LoRA) has emerged as one of the most widely adopted methods for Parameter Efficient Fine-Tuning (PEFT) of Large Language Models (LLMs). LoRA reduces the number of trainable parameters and memory usage while achieving…

Computation and Language · Computer Science 2024-05-03 Justin Zhao , Timothy Wang , Wael Abid , Geoffrey Angus , Arnav Garg , Jeffery Kinnison , Alex Sherstinsky , Piero Molino , Travis Addair , Devvret Rishi

Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling factor can limit or…

Machine Learning · Computer Science 2025-01-14 Jun Liu , Zhenglun Kong , Peiyan Dong , Changdi Yang , Xuan Shen , Pu Zhao , Hao Tang , Geng Yuan , Wei Niu , Wenbin Zhang , Xue Lin , Dong Huang , Yanzhi Wang

While powerful in image-conditioned generation, multimodal large language models (MLLMs) can display uneven performance across demographic groups, highlighting fairness risks. In safety-critical clinical settings, such disparities risk…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Mahesh Bhosale , Abdul Wasi , Shantam Srivastava , Shifa Latif , Tianyu Luan , Mingchen Gao , David Doermann , Xuan Gong

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Machine Learning · Computer Science 2024-12-06 Jason Vega , Junsheng Huang , Gaokai Zhang , Hangoo Kang , Minjia Zhang , Gagandeep Singh

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Parameter-efficient fine-tuning (PEFT) methods, which fine-tune only a subset of model parameters, offer a promising solution by reducing the computational costs of tuning large language models (LLMs) while maintaining their performance.…

Software Engineering · Computer Science 2025-11-25 André Storhaug , Jingyue Li

Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potential biases towards synthetic vs. biological technological…

Computation and Language · Computer Science 2026-03-11 Trent R Northen , Mingxun Wang

Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by…

Computation and Language · Computer Science 2026-04-16 Yarui Cao , Kai Liu

Large language models (LLMs) have been used in many application domains, including cyber security. The application of LLMs in the cyber security domain presents significant opportunities, such as for enhancing threat analysis and malware…

Cryptography and Security · Computer Science 2025-09-18 Adel ElZemity , Budi Arief , Shujun Li

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g.,…

Computation and Language · Computer Science 2023-10-10 Zhiqiang Hu , Lei Wang , Yihuai Lan , Wanyu Xu , Ee-Peng Lim , Lidong Bing , Xing Xu , Soujanya Poria , Roy Ka-Wei Lee

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

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Computation and Language · Computer Science 2024-10-15 Minjun Zhu , Linyi Yang , Yifan Wei , Ningyu Zhang , Yue Zhang

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…

Machine Learning · Computer Science 2024-10-28 Boyi Wei , Kaixuan Huang , Yangsibo Huang , Tinghao Xie , Xiangyu Qi , Mengzhou Xia , Prateek Mittal , Mengdi Wang , Peter Henderson

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Machine Learning · Computer Science 2025-07-15 Seokmin Ko