1 code implementation • 10 Apr 2024 • Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of "Concept Depth" to suggest that more complex concepts are typically acquired in deeper layers.
no code implementations • 6 Apr 2024 • Chong Zhang, Mingyu Jin, Qinkai Yu, Chengzhi Liu, Haochen Xue, Xiaobo Jin
Although there is currently a large amount of research on prompt injection attacks, most of these black-box attacks use heuristic strategies.
no code implementations • 16 Feb 2024 • Mingyu Jin, Hua Tang, Chong Zhang, Qinkai Yu, Chengzhi Liu, Suiyuan Zhu, Yongfeng Zhang, Mengnan Du
However, there is a research gap in the LLMs' preferences in this field.
1 code implementation • 1 Feb 2024 • Mingyu Jin, Qinkai Yu, Dong Shu, Chong Zhang, Lizhou Fan, Wenyue Hua, Suiyuan Zhu, Yanda Meng, Zhenting Wang, Mengnan Du, Yongfeng Zhang
Compared to traditional health management applications, our system has three main advantages: (1) It integrates health reports and medical knowledge into a large model to ask relevant questions to large language model for disease prediction; (2) It leverages a retrieval augmented generation (RAG) mechanism to enhance feature extraction; (3) It incorporates a semi-automated feature updating framework that can merge and delete features to improve accuracy of disease prediction.
1 code implementation • 10 Jan 2024 • Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du
Alternatively, shortening the reasoning steps, even while preserving the key information, significantly diminishes the reasoning abilities of models.
no code implementations • 4 Sep 2023 • Chong Zhang, Mingyu Jin, Qinkai Yu, Haochen Xue, Shreyank N Gowda, Xiaobo Jin
Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training.
1 code implementation • 26 Jun 2023 • Mingyu Jin, Chong Zhang, Qinkai Yu, Haochen Xue, Xiaobo Jin, Xi Yang
Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task.