English
Related papers

Related papers: Shape it Up! Restoring LLM Safety during Finetunin…

200 papers

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Computation and Language · Computer Science 2024-04-02 Yixu Wang , Yan Teng , Kexin Huang , Chengqi Lyu , Songyang Zhang , Wenwei Zhang , Xingjun Ma , Yu-Gang Jiang , Yu Qiao , Yingchun Wang

Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning…

Machine Learning · Computer Science 2025-08-05 Jack Chen , Fazhong Liu , Naruto Liu , Yuhan Luo , Erqu Qin , Harry Zheng , Tian Dong , Haojin Zhu , Yan Meng , Xiao Wang

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

Computation and Language · Computer Science 2024-10-29 Rongwu Xu , Yishuo Cai , Zhenhong Zhou , Renjie Gu , Haiqin Weng , Yan Liu , Tianwei Zhang , Wei Xu , Han Qiu

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Computation and Language · Computer Science 2022-10-20 Chenghao Yang , Xuezhe Ma

Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depends on the selection of training data. Recent advances…

Machine Learning · Computer Science 2026-03-12 Yixiu Mao , Yun Qu , Qi Wang , Heming Zou , Xiangyang Ji

Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects can be fragile: lightweight post-alignment manipulations,…

Artificial Intelligence · Computer Science 2026-05-29 Zhihao Liu , Yifan Wu , Jian Lou , Di Wang , Yuxi Zhou , Yuke Hu

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are…

Cryptography and Security · Computer Science 2024-12-11 Xiangyu Qi , Boyi Wei , Nicholas Carlini , Yangsibo Huang , Tinghao Xie , Luxi He , Matthew Jagielski , Milad Nasr , Prateek Mittal , Peter Henderson

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Computation and Language · Computer Science 2025-02-14 Jingxin Xu , Guoshun Nan , Sheng Guan , Sicong Leng , Yilian Liu , Zixiao Wang , Yuyang Ma , Zhili Zhou , Yanzhao Hou , Xiaofeng Tao

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

Machine Learning · Computer Science 2024-07-11 Zachary Charles , Arun Ganesh , Ryan McKenna , H. Brendan McMahan , Nicole Mitchell , Krishna Pillutla , Keith Rush

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Xiaohan Zou , Jian Kang , George Kesidis , Lu Lin

Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…

Artificial Intelligence · Computer Science 2025-10-28 Bingjie Zhang , Yibo Yang , Zhe Ren , Dandan Guo , Jindong Gu , Philip Torr , Bernard Ghanem

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

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Cryptography and Security · Computer Science 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

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