English
Related papers

Related papers: Emergent Misalignment: Narrow finetuning can produ…

200 papers

Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…

Machine Learning · Computer Science 2025-10-10 Thibaud Gloaguen , Mark Vero , Robin Staab , Martin Vechev

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

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

Context: In the fast-paced evolution of software development, Large Language Models (LLMs) have become indispensable tools for tasks such as code generation, completion, analysis, and bug fixing. Ensuring the robustness of these models…

Software Engineering · Computer Science 2026-02-13 Yang Liu , Armstrong Foundjem , Xingfang Wu , Heng Li , Foutse Khomh

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…

Computation and Language · Computer Science 2024-06-21 Hasan Abed Al Kader Hammoud , Umberto Michieli , Fabio Pizzati , Philip Torr , Adel Bibi , Bernard Ghanem , Mete Ozay

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Software Engineering · Computer Science 2025-12-25 Oussama Ben Sghaier , Kevin Delcourt , Houari Sahraoui

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Computation and Language · Computer Science 2025-11-18 Dongyoon Hahm , Taywon Min , Woogyeol Jin , Kimin Lee

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Computation and Language · Computer Science 2024-09-25 Essa Jan , Nouar AlDahoul , Moiz Ali , Faizan Ahmad , Fareed Zaffar , Yasir Zaki

Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's dependence on user…

Computation and Language · Computer Science 2025-07-25 Kyubeen Han , Junseo Jang , Hongjin Kim , Geunyeong Jeong , Harksoo Kim

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

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

Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of…

Computation and Language · Computer Science 2023-07-13 Jiuding Sun , Chantal Shaib , Byron C. Wallace

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

LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift behavior outside those contexts. In one experiment, we finetune…

Computation and Language · Computer Science 2025-12-11 Jan Betley , Jorio Cocola , Dylan Feng , James Chua , Andy Arditi , Anna Sztyber-Betley , Owain Evans