English
Related papers

Related papers: Re-Emergent Misalignment: How Narrow Fine-Tuning E…

200 papers

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes…

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

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Machine Learning · Computer Science 2026-01-07 Jiawen Zhang , Lipeng He , Kejia Chen , Jian Lou , Jian Liu , Xiaohu Yang , Ruoxi Jia

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Computation and Language · Computer Science 2024-10-01 Sachin Kumar

Large Language Models (LLMs) have shown remarkable progress, but their real-world application necessitates reliable calibration. This study conducts a comprehensive analysis of calibration degradation of LLMs across four dimensions: models,…

Computation and Language · Computer Science 2025-02-11 Hongseok Oh , Wonseok Hwang

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

Computation and Language · Computer Science 2025-06-10 Sooyung Choi , Jaehyeok Lee , Xiaoyuan Yi , Jing Yao , Xing Xie , JinYeong Bak

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Machine Learning · Computer Science 2026-05-05 Sadia Asif , Mohammad Mohammadi Amiri

The focus on safety alignment in large language models (LLMs) has increased significantly due to their widespread adoption across different domains. The scale of LLMs play a contributing role in their success, and the growth in parameter…

Artificial Intelligence · Computer Science 2025-07-29 Rachel S. Y. Teo , Laziz U. Abdullaev , Tan M. Nguyen

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either…

Machine Learning · Computer Science 2026-05-19 Yuhan Huang , Huanran Chen , Yinpeng Dong

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security…

Cryptography and Security · Computer Science 2025-04-08 Shen Li , Liuyi Yao , Lan Zhang , Yaliang Li

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Computation and Language · Computer Science 2023-10-06 Xiangyu Qi , Yi Zeng , Tinghao Xie , Pin-Yu Chen , Ruoxi Jia , Prateek Mittal , Peter Henderson

The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…

Computation and Language · Computer Science 2024-12-18 Xin Yi , Shunfan Zheng , Linlin Wang , Gerard de Melo , Xiaoling Wang , Liang He

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

Machine Learning · Computer Science 2026-04-24 Chengcan Wu , Zhixin Zhang , Zeming Wei , Yihao Zhang , Xiaokun Luan , Meng Sun

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

Artificial Intelligence · Computer Science 2024-12-03 Sanghyun Kim , Moonseok Choi , Jinwoo Shin , Juho Lee

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Machine Learning · Statistics 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

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

Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, we study the problem of…

Computation and Language · Computer Science 2023-08-02 Zhong Zhang , Bang Liu , Junming Shao