no code implementations • 1 Apr 2024 • Weixin Liang, Yaohui Zhang, Zhengxuan Wu, Haley Lepp, Wenlong Ji, Xuandong Zhao, Hancheng Cao, Sheng Liu, Siyu He, Zhi Huang, Diyi Yang, Christopher Potts, Christopher D Manning, James Y. Zou
To address this gap, we conduct the first systematic, large-scale analysis across 950, 965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals, using a population-level statistical framework to measure the prevalence of LLM-modified content over time.
no code implementations • 11 Mar 2024 • Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM).
1 code implementation • 20 Feb 2024 • Jiayi Fu, Xuandong Zhao, Ruihan Yang, Yuansen Zhang, Jiangjie Chen, Yanghua Xiao
Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty.
no code implementations • 18 Feb 2024 • Wenda Xu, Guanglei Zhu, Xuandong Zhao, Liangming Pan, Lei LI, William Yang Wang
Recent studies show that self-feedback improves large language models (LLMs) on certain tasks while worsens other tasks.
1 code implementation • 15 Feb 2024 • André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei LI
We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text.
1 code implementation • 8 Feb 2024 • Xuandong Zhao, Lei LI, Yu-Xiang Wang
In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder.
1 code implementation • 30 Jan 2024 • Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei LI, Yu-Xiang Wang, William Yang Wang
In this paper, we propose the weak-to-strong jailbreaking attack, an efficient method to attack aligned LLMs to produce harmful text.
1 code implementation • 24 Oct 2023 • Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng
The burgeoning capabilities of advanced large language models (LLMs) such as ChatGPT have led to an increase in synthetic content generation with implications across a variety of sectors, including media, cybersecurity, public discourse, and education.
4 code implementations • 30 Jun 2023 • Xuandong Zhao, Prabhanjan Ananth, Lei LI, Yu-Xiang Wang
We propose a robust and high-quality watermark method, Unigram-Watermark, by extending an existing approach with a simplified fixed grouping strategy.
1 code implementation • 12 Jun 2023 • Yuqing Zhu, Xuandong Zhao, Chuan Guo, Yu-Xiang Wang
Most existing approaches of differentially private (DP) machine learning focus on private training.
1 code implementation • 2 Jun 2023 • Xuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang, Lei LI
However, if we do not require the watermarked image to look the same as the original one, watermarks that keep the image semantically similar can be an alternative defense against our attack.
2 code implementations • 6 Feb 2023 • Xuandong Zhao, Yu-Xiang Wang, Lei LI
We can then detect the secret message by probing a suspect model to tell if it is distilled from the protected one.
2 code implementations • 14 Dec 2022 • Xuandong Zhao, Siqi Ouyang, Zhiguo Yu, Ming Wu, Lei LI
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data?
1 code implementation • 7 Oct 2022 • Xuandong Zhao, Lei LI, Yu-Xiang Wang
We prove that a protected model still retains the original accuracy within a certain bound.
1 code implementation • NAACL 2022 • Xuandong Zhao, Lei LI, Yu-Xiang Wang
Large language models are shown to memorize privacy information such as social security numbers in training data.
1 code implementation • Findings (ACL) 2022 • Xuandong Zhao, Zhiguo Yu, Ming Wu, Lei LI
How to learn highly compact yet effective sentence representation?
no code implementations • 23 Jan 2021 • Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang
We consider the problem of estimating a function from $n$ noisy samples whose discrete Total Variation (TV) is bounded by $C_n$.
no code implementations • 19 Jul 2020 • Xuandong Zhao, Jinbao Xue, Jin Yu, Xi Li, Hongxia Yang
In real-world applications, networks usually consist of billions of various types of nodes and edges with abundant attributes.
no code implementations • 1 Oct 2019 • Jiaming Guo, Wei Qiu, Xiang Li, Xuandong Zhao, Ning Guo, Quanzheng Li
Imaging-based early diagnosis of Alzheimer Disease (AD) has become an effective approach, especially by using nuclear medicine imaging techniques such as Positron Emission Topography (PET).