English
Related papers

Related papers: Head-Specific Intervention Can Induce Misaligned A…

200 papers

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

Computation and Language · Computer Science 2026-04-13 Hadas Orgad , Boyi Wei , Kaden Zheng , Martin Wattenberg , Peter Henderson , Seraphina Goldfarb-Tarrant , Yonatan Belinkov

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Machine Learning · Computer Science 2025-08-14 Birong Pan , Mayi Xu , Qiankun Pi , Jianhao Chen , Yuanyuan Zhu , Ming Zhong , Tieyun Qian

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Cryptography and Security · Computer Science 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

Cryptography and Security · Computer Science 2025-12-30 Yangyang Guo , Yangyan Li , Mohan Kankanhalli

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

Computation and Language · Computer Science 2023-12-19 Bingchen Zhao , Haoqin Tu , Chen Wei , Jieru Mei , Cihang Xie

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Machine Learning · Computer Science 2025-06-06 Tom A. Lamb , Adam Davies , Alasdair Paren , Philip H. S. Torr , Francesco Pinto

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an…

Cryptography and Security · Computer Science 2025-11-25 Peng Zhang , Peijie Sun

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…

Computation and Language · Computer Science 2025-07-08 Annika M Schoene , Cansu Canca

Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate…

Computation and Language · Computer Science 2026-01-13 Wenhong Zhu , Weinan Zhang , Rui Wang

Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper grounding. However, LLM hallucination may result in robots…

Artificial Intelligence · Computer Science 2025-02-12 Kaiqu Liang , Zixu Zhang , Jaime Fernández Fisac

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…

Computation and Language · Computer Science 2024-04-05 Xuansheng Wu , Wenlin Yao , Jianshu Chen , Xiaoman Pan , Xiaoyang Wang , Ninghao Liu , Dong Yu

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

Computation and Language · Computer Science 2025-10-28 Havva Alizadeh Noughabi , Julien Serbanescu , Fattane Zarrinkalam , Ali Dehghantanha

Large Language Models (LLMs) are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform…

Cryptography and Security · Computer Science 2025-12-02 Omar Farooq Khan Suri , John McCrae

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Machine Learning · Computer Science 2026-04-07 Soham Gadgil , Chris Lin , Su-In Lee

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…

Artificial Intelligence · Computer Science 2024-03-25 Yixuan Wang , Ruochen Jiao , Sinong Simon Zhan , Chengtian Lang , Chao Huang , Zhaoran Wang , Zhuoran Yang , Qi Zhu

Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across tasks and languages, revolutionizing natural language processing. This paper investigates the naturally emerging representation alignment in LLMs,…

Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…

Cryptography and Security · Computer Science 2025-09-23 Rui Yang , Michael Fu , Chakkrit Tantithamthavorn , Chetan Arora , Gunel Gulmammadova , Joey Chua

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

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Cryptography and Security · Computer Science 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Cryptography and Security · Computer Science 2025-05-23 Biao Yi , Tiansheng Huang , Baolei Zhang , Tong Li , Lihai Nie , Zheli Liu , Li Shen