English
Related papers

Related papers: Guardrails in Logit Space: Safety Token Regulariza…

200 papers

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Machine Learning · Computer Science 2025-08-19 Minseon Kim , Jin Myung Kwak , Lama Alssum , Bernard Ghanem , Philip Torr , David Krueger , Fazl Barez , Adel Bibi

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognized paradigm frames…

Computation and Language · Computer Science 2025-08-12 Biao Yi , Jiahao Li , Baolei Zhang , Lihai Nie , Tong Li , Tiansheng Huang , Zheli Liu

The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or internal representations, we observe that they can be effectively…

Cryptography and Security · Computer Science 2026-05-11 Guoxin Lu , Letian Sha , Qing Wang , Peijie Sun , Hao Zhou , Hua Dai , Fu Xiao

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…

Computation and Language · Computer Science 2025-11-20 Xudong Han , Junjie Yang , Tianyang Wang , Ziqian Bi , Xinyuan Song , Junfeng Hao , Junhao Song

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

Computation and Language · Computer Science 2025-10-20 Aaron Zheng , Mansi Rana , Andreas Stolcke

Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…

Computation and Language · Computer Science 2025-06-05 Chong Li , Jiajun Zhang , Chengqing Zong

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Cryptography and Security · Computer Science 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

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

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Machine Learning · Computer Science 2026-02-10 Xuanqi Zhang , Haoyang Shang , Xiaoxiao Li

Optimizing noisy functions online, when evaluating the objective requires experiments on a deployed system, is a crucial task arising in manufacturing, robotics and many others. Often, constraints on safe inputs are unknown ahead of time,…

Optimization and Control · Mathematics 2023-06-06 Ilnura Usmanova , Yarden As , Maryam Kamgarpour , Andreas Krause

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Machine Learning · Computer Science 2026-02-13 Zhaoxin Wang , Jiaming Liang , Fengbin Zhu , Weixiang Zhao , Junfeng Fang , Jiayi Ji , Handing Wang , Tat-Seng Chua

Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Mingkun Yang , Biao Yang , Minghui Liao , Yingying Zhu , Xiang Bai

Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is…

Computation and Language · Computer Science 2026-04-15 Yuhan Song , Linhao Zhang , Chuhan Wu , Aiwei Liu , Wei Jia , Houfeng Wang , Xiao Zhou

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Caiyuan Zheng , Hui Li , Seon-Min Rhee , Seungju Han , Jae-Joon Han , Peng Wang

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Cryptography and Security · Computer Science 2025-06-06 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Zachary Yahn , Yichang Xu , Ling Liu

Efficiently fine-tuning Large Language Models (LLMs) for specific tasks presents a considerable challenge in natural language processing. Traditional methods, like prompt or prefix tuning, typically rely on arbitrary tokens for training,…

Computation and Language · Computer Science 2024-04-16 Md. Kowsher , Md. Shohanur Islam Sobuj , Asif Mahmud , Nusrat Jahan Prottasha , Prakash Bhat

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Computation and Language · Computer Science 2025-05-27 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…

Computers and Society · Computer Science 2026-02-03 Guanghao Zhou , Panjia Qiu , Cen Chen , Hongyu Li , Mingyuan Chu , Xin Zhang , Jun Zhou
‹ Prev 1 3 4 5 6 7 10 Next ›