English
Related papers

Related papers: Smoothed Embeddings for Robust Language Models

200 papers

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Computation and Language · Computer Science 2025-07-25 Xuandong Zhao , Xianjun Yang , Tianyu Pang , Chao Du , Lei Li , Yu-Xiang Wang , William Yang Wang

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge…

Computation and Language · Computer Science 2024-06-07 Haozheng Luo , Jiahao Yu , Wenxin Zhang , Jialong Li , Jerry Yao-Chieh Hu , Xinyu Xing , Han Liu

Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Kai Qiu , Huishuai Zhang , Zhirong Wu , Stephen Lin

Randomized smoothing is the dominant standard for provable defenses against adversarial examples. Nevertheless, this method has recently been proven to suffer from important information theoretic limitations. In this paper, we argue that…

Machine Learning · Computer Science 2022-06-06 Raphael Ettedgui , Alexandre Araujo , Rafael Pinot , Yann Chevaleyre , Jamal Atif

A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models' robustness against perturbations…

Computation and Language · Computer Science 2023-06-05 Xiuying Chen , Guodong Long , Chongyang Tao , Mingzhe Li , Xin Gao , Chengqi Zhang , Xiangliang Zhang

Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-30 Phurich Saengthong , Tomoya Nishida , Kota Dohi , Natsuo Yamashita , Yohei Kawaguchi

Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple Deep Neural Networks (DNNs) has shown state-of-the-art performances due to its variance reduction effect over Gaussian…

Machine Learning · Computer Science 2025-04-14 Kun Fang , Qinghua Tao , Yingwen Wu , Tao Li , Xiaolin Huang , Jie Yang

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Computation and Language · Computer Science 2026-05-12 Yan Sun , Guoxia Wang , Jinle Zeng , JiaBin Yang , Shuai Li , Li Shen , Dacheng Tao , DianHai Yu , Haifeng Wang

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

Machine Learning · Computer Science 2024-10-31 Yashvir S. Grewal , Edwin V. Bonilla , Thang D. Bui

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and…

Computation and Language · Computer Science 2024-09-19 Xingyun Hong , Yan Shao , Zhilin Wang , Manni Duan , Jin Xiongnan

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

Machine Learning · Computer Science 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, particularly in safety-critical applications. We propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Marwane Hariat , Olivier Laurent , Rémi Kazmierczak , Shihao Zhang , Andrei Bursuc , Angela Yao , Gianni Franchi

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

Cryptography and Security · Computer Science 2025-10-20 Adam Swanda , Amy Chang , Alexander Chen , Fraser Burch , Paul Kassianik , Konstantin Berlin

Randomized Smoothing (RS) is a promising method for obtaining robustness certificates by evaluating a base model under noise. In this work, we: (i) theoretically motivate why ensembles are a particularly suitable choice as base models for…

Machine Learning · Computer Science 2022-03-31 Miklós Z. Horváth , Mark Niklas Müller , Marc Fischer , Martin Vechev

Large language models (LLMs) have recently demonstrated excellent performance in text embedding tasks. Previous work usually use LoRA to fine-tune existing LLMs, which are limited by the data and training gap between LLMs and embedding…

Computation and Language · Computer Science 2025-09-17 Shiyu Li , Yang Tang , Ruijie Liu , Shi-Zhe Chen , Xi Chen

Large language models (LLMs) struggle with maintaining accurate knowledge due to conflicting/outdated parametric memories. While locate-and-edit methods address this, their reliance on models' internal representations leads to robustness…

Computation and Language · Computer Science 2025-05-23 Jianhao Yan , Futing Wang , Yun Luo , Yafu Li , Yue Zhang

Large Language Models (LLMs) are seeing significant adoption in every type of organization due to their exceptional generative capabilities. However, LLMs are found to be vulnerable to various adversarial attacks, particularly prompt…

Cryptography and Security · Computer Science 2024-10-30 Md. Ahsan Ayub , Subhabrata Majumdar