English
Related papers

Related papers: Shifting the Gradient: Understanding How Defensive…

200 papers

Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…

Computation and Language · Computer Science 2022-12-02 Zhuosheng Zhang , Hai Zhao , Masao Utiyama , Eiichiro Sumita

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

Formally verifying the correctness of mathematical proofs is more accessible than ever, however, the learning curve remains steep for many of the state-of-the-art interactive theorem provers (ITP). Deriving the most appropriate subsequent…

Logic in Computer Science · Computer Science 2024-11-05 Liao Zhang , David M. Cerna , Cezary Kaliszyk

Automatic Speech Recognition (ASR) systems have attained unprecedented performance with large speech models pre-trained based on self-supervised speech representation learning. However, these pre-trained speech models suffer from…

Computation and Language · Computer Science 2023-05-29 Eunseop Yoon , Hee Suk Yoon , John Harvill , Mark Hasegawa-Johnson , Chang D. Yoo

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

Computation and Language · Computer Science 2023-10-09 Zhengxiang Shi , Aldo Lipani

The rapid increase in the parameter counts of Large Language Models (LLMs), which often reach into the billions or even trillions, presents significant challenges for their practical deployment, particularly in resource-constrained…

Machine Learning · Computer Science 2025-11-18 Yi Cao , Wei-Jie Xu , Yucheng Shen , Weijie Shi , Chi-Min Chan , Jianfeng Qu , Jiajie Xu

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…

Cryptography and Security · Computer Science 2025-08-22 Hengyu An , Jinghuai Zhang , Tianyu Du , Chunyi Zhou , Qingming Li , Tao Lin , Shouling Ji

In the recent years, Physics Informed Neural Networks (PINNs) have received strong interest as a method to solve PDE driven systems, in particular for data assimilation purpose. This method is still in its infancy, with many shortcomings…

Machine Learning · Computer Science 2025-03-20 Nilo Schwencke , Cyril Furtlehner

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore…

Machine Learning · Computer Science 2020-10-07 Pengfei Xia , Bin Li

Fine-tuning large language models is becoming ever more impractical due to their rapidly-growing scale. This motivates the use of parameter-efficient adaptation methods such as prompt tuning (PT), which adds a small number of tunable…

Computation and Language · Computer Science 2023-02-23 Simeng Sun , Yang Liu , Dan Iter , Chenguang Zhu , Mohit Iyyer

The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…

Cryptography and Security · Computer Science 2024-12-10 Guoshenghui Zhao , Eric Song

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…

Computation and Language · Computer Science 2025-02-19 Huawei Lin , Yingjie Lao , Tong Geng , Tan Yu , Weijie Zhao

This work presents a novel systematic methodology to analyse the capabilities and limitations of Large Language Models (LLMs) with feedback from a formal inference engine, on logic theory induction. The analysis is complexity-graded w.r.t.…

Computation and Language · Computer Science 2025-01-15 João Pedro Gandarela , Danilo S. Carvalho , André Freitas

The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult speaker. To apply a similar approach to analyze neural language…

Computation and Language · Computer Science 2022-04-07 Leshem Choshen , Guy Hacohen , Daphna Weinshall , Omri Abend

Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM…

Cryptography and Security · Computer Science 2025-07-04 Sizhe Chen , Arman Zharmagambetov , Saeed Mahloujifar , Kamalika Chaudhuri , David Wagner , Chuan Guo

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as…

Computation and Language · Computer Science 2025-03-21 Anmol Goel , Yaxi Hu , Iryna Gurevych , Amartya Sanyal

Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in…

Computation and Language · Computer Science 2023-05-16 Damai Dai , Yutao Sun , Li Dong , Yaru Hao , Shuming Ma , Zhifang Sui , Furu Wei

Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Lin Luo , Xin Wang , Bojia Zi , Shihao Zhao , Xingjun Ma , Yu-Gang Jiang

Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and then train a model to recover the tokens at the masked…

Computation and Language · Computer Science 2020-08-18 Liang Chen