English
Related papers

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

200 papers

Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes remain limited. We present a controlled comparison of six…

Computation and Language · Computer Science 2026-01-21 Daniel Vennemeyer , Punya Syon Pandey , Phan Anh Duong , Michael Umeokoli , Samuel Ratnam

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Computation and Language · Computer Science 2026-04-21 Zhexin Zhang , Xian Qi Loye , Victor Shea-Jay Huang , Junxiao Yang , Qi Zhu , Shiyao Cui , Fei Mi , Lifeng Shang , Yingkang Wang , Hongning Wang , Minlie Huang

Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning. To preserve safety alignment during fine-tuning, a widely used strategy is to jointly…

Computation and Language · Computer Science 2026-03-12 Zhouxiang Fang , Jiawei Zhou , Hanjie Chen

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

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

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Machine Learning · Computer Science 2025-04-04 Abhay Kumar , Louis Owen , Nilabhra Roy Chowdhury , Fabian Güra

Data is a crucial element in large language model (LLM) alignment. Recent studies have explored using LLMs for efficient data collection. However, LLM-generated data often suffers from quality issues, with underrepresented or absent aspects…

Computation and Language · Computer Science 2024-10-08 Fei Wang , Ninareh Mehrabi , Palash Goyal , Rahul Gupta , Kai-Wei Chang , Aram Galstyan

Recent advancements in Large Language Models (LLMs) have significantly improved their capabilities in natural language processing and code synthesis, enabling more complex applications across different fields. This paper explores the…

Cryptography and Security · Computer Science 2024-10-30 Mohammad Setak , Pooria Madani

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Computation and Language · Computer Science 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…

Machine Learning · Computer Science 2024-10-28 Boyi Wei , Kaixuan Huang , Yangsibo Huang , Tinghao Xie , Xiangyu Qi , Mengzhou Xia , Prateek Mittal , Mengdi Wang , Peter Henderson

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

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

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

Computation and Language · Computer Science 2026-01-06 Dianyun Wang , Qingsen Ma , Yuhu Shang , Zhifeng Lu , Zhenbo Xu , Lechen Ning , Huijia Wu , Zhaofeng He

As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse…

Machine Learning · Computer Science 2025-06-03 Saad Hossain , Samanvay Vajpayee , Sirisha Rambhatla

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Machine Learning · Computer Science 2026-04-20 Zixuan Weng , Jinghuai Zhang , Kunlin Cai , Ying Li , Peiran Wang , Yuan Tian

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

Modern language models (LMs) have gained widespread acceptance in everyday and professional contexts, particularly in programming. An essential procedure enabling this adoption is instruction tuning, which substantially enhances LMs'…

Cryptography and Security · Computer Science 2024-07-15 Jingxuan He , Mark Vero , Gabriela Krasnopolska , Martin Vechev

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Cryptography and Security · Computer Science 2025-02-19 Xiaoqun Liu , Jiacheng Liang , Luoxi Tang , Muchao Ye , Weicheng Ma , Zhaohan Xi

We use Machine Learning (ML) and system identification validation approaches to estimate neural network models of large-scale Deformable Mirrors (DMs) used in Adaptive Optics (AO) systems. To obtain the training, validation, and test data…

Systems and Control · Electrical Eng. & Systems 2019-11-19 Aleksandar Haber