English
Related papers

Related papers: Lightweight Safety Guardrails Using Fine-tuned BER…

200 papers

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric…

Machine Learning · Computer Science 2025-11-25 Thong Bach , Thanh Nguyen-Tang , Dung Nguyen , Thao Minh Le , Truyen Tran

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…

Computation and Language · Computer Science 2024-07-22 Pradyumna Saligram , Andrew Lanpouthakoun

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

Artificial Intelligence · Computer Science 2026-02-03 Jingnan Zheng , Jingjun Xu , Yanzhen Luo , Chenhang Cui , Gelei Deng , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance by dynamically assigning queries to the most appropriate model based on query complexity. Despite recent advances…

Computation and Language · Computer Science 2025-04-11 Aly M. Kassem , Bernhard Schölkopf , Zhijing Jin

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However,…

Computation and Language · Computer Science 2023-09-01 Souvik Kundu , Sharath Nittur Sridhar , Maciej Szankin , Sairam Sundaresan

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause…

Computation and Language · Computer Science 2025-01-07 Joao Fonseca , Andrew Bell , Julia Stoyanovich

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Computation and Language · Computer Science 2025-03-25 Xunguang Wang , Wenxuan Wang , Zhenlan Ji , Zongjie Li , Pingchuan Ma , Daoyuan Wu , Shuai Wang

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raises the possibility of replacing human roles that bottleneck existing information…

Computation and Language · Computer Science 2025-12-18 Kester Clegg , Richard Hawkins , Ibrahim Habli , Tom Lawton

We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model (LLM) interactions, optimized specifically for production deployment. Recent advances in…

Machine Learning · Computer Science 2025-06-10 Yash Datta , Sharath Rajasekar

As large language models (LLMs) expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence…

Cryptography and Security · Computer Science 2026-02-05 Xiaoyan Zhang , Dongyang Lyu , Xiaoqi Li

Large language models (LLMs), such as ChatGPT, have emerged with astonishing capabilities approaching artificial general intelligence. While providing convenience for various societal needs, LLMs have also lowered the cost of generating…

Computation and Language · Computer Science 2023-08-28 Zhenhua Wang , Wei Xie , Kai Chen , Baosheng Wang , Zhiwen Gui , Enze Wang

The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…

Computation and Language · Computer Science 2025-09-12 Amirhossein Dabiriaghdam , Lele Wang

Large language models (LLMs) have significantly facilitated human life, and prompt engineering has improved the efficiency of these models. However, recent years have witnessed a rise in prompt engineering-empowered attacks, leading to…

Cryptography and Security · Computer Science 2025-02-03 Haiyang Huang , Tianhui Meng , Weijia Jia

Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…

Computation and Language · Computer Science 2023-08-01 Ting Jiang , Shaohan Huang , Zhongzhi Luan , Deqing Wang , Fuzhen Zhuang

Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated…

Cryptography and Security · Computer Science 2024-06-03 Haibo Jin , Andy Zhou , Joe D. Menke , Haohan Wang

Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across…

Artificial Intelligence · Computer Science 2026-04-21 Difan Jiao , Yilun Liu , Ye Yuan , Zhenwei Tang , Linfeng Du , Haolun Wu , Ashton Anderson

Input-output safeguards are used to detect anomalies in the traces produced by Large Language Models (LLMs) systems. These detectors are at the core of diverse safety-critical applications such as real-time monitoring, offline evaluation of…

Cryptography and Security · Computer Science 2024-06-04 Diego Dorn , Alexandre Variengien , Charbel-Raphaël Segerie , Vincent Corruble