Zobrazeno 1 - 10
of 1 653
pro vyhledávání: '"Wang Haining"'
While large language models (LLMs) show promise in hospitality and tourism, their ability to provide unbiased service across demographic groups remains unclear. This paper explores gender and ethnic biases when LLMs are utilized as travel planning as
Externí odkaz:
http://arxiv.org/abs/2410.17333
Autor:
Wang, Haining, Clark, Jason, McKelvey, Hannah, Sterman, Leila, Gao, Zheng, Tian, Zuoyu, Kübler, Sandra, Liu, Xiaozhong
A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language. To address this challenge in science communication, we introduce a reinforcement learning framewor
Externí odkaz:
http://arxiv.org/abs/2410.17088
Autor:
Yang, Yuzhe, Zhang, Yifei, Hu, Yan, Guo, Yilin, Gan, Ruoli, He, Yueru, Lei, Mingcong, Zhang, Xiao, Wang, Haining, Xie, Qianqian, Huang, Jimin, Yu, Honghai, Wang, Benyou
This paper introduces the UCFE: User-Centric Financial Expertise benchmark, an innovative framework designed to evaluate the ability of large language models (LLMs) to handle complex real-world financial tasks. UCFE benchmark adopts a hybrid approach
Externí odkaz:
http://arxiv.org/abs/2410.14059
The use of transformers for vision tasks has challenged the traditional dominant role of convolutional neural networks (CNN) in computer vision (CV). For image classification tasks, Vision Transformer (ViT) effectively establishes spatial relationshi
Externí odkaz:
http://arxiv.org/abs/2409.13828
The rapid proliferation of Internet of Things (IoT) devices across multiple sectors has escalated serious network security concerns. This has prompted ongoing research in Machine Learning (ML)-based Intrusion Detection Systems (IDSs) for cyber-attack
Externí odkaz:
http://arxiv.org/abs/2408.07152
Autor:
Wang, Haining, Clark, Jason
Standing at the forefront of knowledge dissemination, digital libraries curate vast collections of scientific literature. However, these scholarly writings are often laden with jargon and tailored for domain experts rather than the general public. As
Externí odkaz:
http://arxiv.org/abs/2408.03899
Federated Learning (FL) exposes vulnerabilities to targeted poisoning attacks that aim to cause misclassification specifically from the source class to the target class. However, using well-established defense frameworks, the poisoning impact of thes
Externí odkaz:
http://arxiv.org/abs/2407.09958
Nowadays, the open-source software (OSS) ecosystem suffers from security threats of software supply chain (SSC) attacks. Interpreted OSS malware plays a vital role in SSC attacks, as criminals have an arsenal of attack vectors to deceive users into i
Externí odkaz:
http://arxiv.org/abs/2407.08532
Real-time Clock (RTC) has been widely used in various real-time systems to provide precise system time. In this paper, we reveal a new security vulnerability of the RTC circuit, where the internal storage time or timestamp can be arbitrarily modified
Externí odkaz:
http://arxiv.org/abs/2407.06853
Internet censorship is typically enforced by authorities to achieve information control for a certain group of Internet users. So far existing censorship studies have primarily focused on country-level characterization because (1) in many cases, cens
Externí odkaz:
http://arxiv.org/abs/2407.04213