Zobrazeno 1 - 10
of 1 877
pro vyhledávání: '"Wang, JunHui"'
How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review
Autor:
Zhu, Xichou, Liu, Yang, Shen, Zhou, Liu, Yi, Li, Min, Chen, Yujun, John, Benzi, Ma, Zhenzhen, Hu, Tao, Li, Zhi, Yang, Bolong, Wang, Manman, Xie, Zongxing, Liu, Peng, Cai, Dan, Wang, Junhui
The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy compliance and
Externí odkaz:
http://arxiv.org/abs/2409.02375
Autor:
Liu, Yang, Zhu, Xichou, Shen, Zhou, Liu, Yi, Li, Min, Chen, Yujun, John, Benzi, Ma, Zhenzhen, Hu, Tao, Li, Zhi, Xu, Zhiyang, Luo, Wei, Wang, Junhui
Large Language Models (LLMs) have recently displayed their extraordinary capabilities in language understanding. However, how to comprehensively assess the sentiment capabilities of LLMs continues to be a challenge. This paper investigates the abilit
Externí odkaz:
http://arxiv.org/abs/2409.02370
As network data has become increasingly prevalent, a substantial amount of attention has been paid to the privacy issue in publishing network data. One of the critical challenges for data publishers is to preserve the topological structures of the or
Externí odkaz:
http://arxiv.org/abs/2406.14772
General-purpose processor vendors have integrated customized accelerator in their products due to the widespread use of General Matrix-Matrix Multiplication (GEMM) kernels. However, it remains a challenge to further improve the flexibilityand scalabi
Externí odkaz:
http://arxiv.org/abs/2404.19180
Directed acyclic graph (DAG) has been widely employed to represent directional relationships among a set of collected nodes. Yet, the available data in one single study is often limited for accurate DAG reconstruction, whereas heterogeneous data may
Externí odkaz:
http://arxiv.org/abs/2310.10239
Dynamic networks consist of a sequence of time-varying networks, and it is of great importance to detect the network change points. Most existing methods focus on detecting abrupt change points, necessitating the assumption that the underlying networ
Externí odkaz:
http://arxiv.org/abs/2310.08268
We propose a general approach to evaluating the performance of robust estimators based on adversarial losses under misspecified models. We first show that adversarial risk is equivalent to the risk induced by a distributional adversarial attack under
Externí odkaz:
http://arxiv.org/abs/2309.00771
In this article, we consider the problem of testing whether two latent position random graphs are correlated. We propose a test statistic based on the kernel method and introduce the estimation procedure based on the spectral decomposition of adjacen
Externí odkaz:
http://arxiv.org/abs/2303.10690
The chain graph model admits both undirected and directed edges in one graph, where symmetric conditional dependencies are encoded via undirected edges and asymmetric causal relations are encoded via directed edges. Though frequently encountered in p
Externí odkaz:
http://arxiv.org/abs/2303.01031
Crowdsourcing has emerged as an alternative solution for collecting large scale labels. However, the majority of recruited workers are not domain experts, so their contributed labels could be noisy. In this paper, we propose a two-stage model to pred
Externí odkaz:
http://arxiv.org/abs/2302.02304