English
Related papers

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

200 papers

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence · Computer Science 2026-02-03 Abhishek Mishra , Mugilan Arulvanan , Reshma Ashok , Polina Petrova , Deepesh Suranjandass , Donnie Winkelmann

Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation. Despite defenses against malicious short…

Computation and Language · Computer Science 2024-05-27 Yu Fu , Wen Xiao , Jia Chen , Jiachen Li , Evangelos Papalexakis , Aichi Chien , Yue Dong

Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe…

Computation and Language · Computer Science 2026-03-24 Xu Zhao , Xiting Wang , Weiran Shen

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Cryptography and Security · Computer Science 2026-05-19 Tim Beyer , Sophie Xhonneux , Simon Geisler , Gauthier Gidel , Leo Schwinn , Stephan Günnemann

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Cryptography and Security · Computer Science 2025-05-27 Haoyu Wang , Zeyu Qin , Yifei Zhao , Chao Du , Min Lin , Xueqian Wang , Tianyu Pang

As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) will become essential due to their efficiency in reducing computation…

Machine Learning · Computer Science 2025-01-06 Mingjie Li , Wai Man Si , Michael Backes , Yang Zhang , Yisen Wang

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Large Language Model (LLM) alignment aims to ensure that LLM outputs match with human values. Researchers have demonstrated the severity of alignment problems with a large spectrum of jailbreak techniques that can induce LLMs to produce…

Computation and Language · Computer Science 2024-02-06 Xiaolong Jin , Zhuo Zhang , Xiangyu Zhang

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety…

Computation and Language · Computer Science 2025-10-14 Seokil Ham , Yubin Choi , Yujin Yang , Seungju Cho , Younghun Kim , Changick Kim

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is currently a lack of safety study on this novel architecture.…

Cryptography and Security · Computer Science 2025-11-27 Zhixin Xie , Xurui Song , Jun Luo

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing…

Cryptography and Security · Computer Science 2026-03-16 Jinman Wu , Yi Xie , Shiqian Zhao , Xiaofeng Chen

Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing…

Cryptography and Security · Computer Science 2025-11-25 Xiaoning Dong , Wenbo Hu , Wei Xu , Tianxing He

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate…

Computation and Language · Computer Science 2024-04-16 Geyang Guo , Ranchi Zhao , Tianyi Tang , Wayne Xin Zhao , Ji-Rong Wen

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Machine Learning · Computer Science 2024-02-28 Heegyu Kim , Sehyun Yuk , Hyunsouk Cho

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

Artificial Intelligence · Computer Science 2026-02-03 Yihao Xue , Baharan Mirzasoleiman

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety alignment, e.g., by greatly increasing susceptibility to…

Machine Learning · Computer Science 2026-01-16 Jiawen Zhang , Yangfan Hu , Kejia Chen , Lipeng He , Jiachen Ma , Jian Lou , Dan Li , Jian Liu , Xiaohu Yang , Ruoxi Jia

Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-resource languages (HRLs) like English. Existing solutions, such…

Machine Learning · Computer Science 2026-02-27 Jiaming Liang , Zhaoxin Wang , Handing Wang

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jailbreak attack methods mainly focus on discrete prompt…

Cryptography and Security · Computer Science 2025-02-18 Guanghao Zhou , Panjia Qiu , Mingyuan Fan , Cen Chen , Mingyuan Chu , Xin Zhang , Jun Zhou