English
Related papers

Related papers: Benign Samples Matter! Fine-tuning On Outlier Beni…

200 papers

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 work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected,…

Machine Learning · Computer Science 2025-06-16 Edward Turner , Anna Soligo , Mia Taylor , Senthooran Rajamanoharan , Neel Nanda

With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever.…

Cryptography and Security · Computer Science 2025-07-28 Hao Li , Lijun Li , Zhenghao Lu , Xianyi Wei , Rui Li , Jing Shao , Lei Sha

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

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

Cryptography and Security · Computer Science 2025-07-30 Zixuan Chen , Weikai Lu , Xin Lin , Ziqian Zeng

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

The spread of fake news, polarizing, politically biased, and harmful content on online platforms has been a serious concern. With large language models becoming a promising approach, however, no study has properly benchmarked their…

Computation and Language · Computer Science 2025-09-10 Michele Joshua Maggini , Dhia Merzougui , Rabiraj Bandyopadhyay , Gaël Dias , Fabrice Maurel , Pablo Gamallo

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

Computation and Language · Computer Science 2024-03-15 Haoran Yang , Yumeng Zhang , Jiaqi Xu , Hongyuan Lu , Pheng Ann Heng , Wai Lam

The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to…

Machine Learning · Computer Science 2024-07-31 Sara Abdali , Jia He , CJ Barberan , Richard Anarfi

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…

Artificial Intelligence · Computer Science 2025-01-17 Huandong Wang , Wenjie Fu , Yingzhou Tang , Zhilong Chen , Yuxi Huang , Jinghua Piao , Chen Gao , Fengli Xu , Tao Jiang , Yong Li

Despite significant ongoing efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behaviors, including through the use of adversarial suffixes.…

Cryptography and Security · Computer Science 2024-12-20 Wei Zhao , Zhe Li , Yige Li , Jun Sun

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Computation and Language · Computer Science 2022-05-03 Shoujie Tong , Qingxiu Dong , Damai Dai , Yifan song , Tianyu Liu , Baobao Chang , Zhifang Sui

There is ongoing debate about whether large language models (LLMs) can serve as substitutes for human participants in survey and experimental research. While recent work in fields such as marketing and psychology has explored the potential…

Computation and Language · Computer Science 2025-12-30 Steven Wang , Kyle Hunt , Shaojie Tang , Kenneth Joseph

Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across…

Cryptography and Security · Computer Science 2026-05-20 John T. Halloran , Noopur S. Bhatt

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Cryptography and Security · Computer Science 2024-06-11 Yuanpu Cao , Bochuan Cao , Jinghui Chen

As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM…

Computation and Language · Computer Science 2024-04-09 Qiusi Zhan , Richard Fang , Rohan Bindu , Akul Gupta , Tatsunori Hashimoto , Daniel Kang

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for…

Software Engineering · Computer Science 2024-07-26 Hongwei Jin , George Papadimitriou , Krishnan Raghavan , Pawel Zuk , Prasanna Balaprakash , Cong Wang , Anirban Mandal , Ewa Deelman