Mingyu Jin

About Me

I am a first-year PhD student at the Department of Computer Science, Rutgers University-New Brunswick. Currently, I am working closely with Prof. Yongfeng Zhang on XAI, LLM-based Agents, Data Mining. My research interests lie in Explainable AI(XAI), Trustworthy Agents, and AI4Science, emphasizing large language models(LLMs). Before that, I obtained my bachelor’s degree from the University of Liverpool. I was an intern student guided by Prof. Mengnan Du worked in XAI before I received my PhD offer.

Research Interests

XAI, LLM Agent, AI4SCIENCE, Data Mining

News

• [11/2024] Check our new version about the paper LLM Agent Operating System
• [10/2024] One paper was accepted by EMNLP 2024 Demo Track
• [09/2024] Two paper was accepted by EMNLP 2024
• [09/2024] One paper was accepted by ICDM 2024
• [09/2024] One paper was accepted by ACML 2024
• [08/2024] One survey was accepted by Journal of Healthcare Informatics Research(IF=5.7)
• [08/2024] Please check our preprint and code about Stockagent
• [07/2024] Please check our preprint about Manipulating Uncertainty in Large Language Models
• [07/2024] One Paper was accepted by COLM 2024
• [07/2024] Our Paper: Simulating Alien Civilizations with LLM-based Agent was reported by this website.
• [07/2024] One paper was accepted by ECAI 2024 as Oral.
• [06/2024] I was invited to give a talk about Prollm@Nice
• [06/2024] One paper was accepted by TiFA@ICML 2024
• [05/2024] One paper was accepted by ACL 2024, thanks@Qinkai
• [04/2024] Check Our Preprint: Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers? about the concept depth in LLM.
• [02/2024] Give a talk@Zhiyuan
• [02/2024] Get my PhD offer from Rutgers University!!! I will join the WISE lab in 2024 fall.
• [01/2024] Start my trip to New York, the most unforgettable journey of my life.
• [01/2024] Check Our Preprint: The Impact of Reasoning Step Length on Large Language Models about how Cot works.
• [12/2023] One paper was accepted by AAAI 2024
• [09/2023] Started my visit to Northwestern University!!!
• [07/2023] One paper was accepted by ICONIP 2023.

Services

• Conference reviewing: RecSys 2024, NeurIPS 2024, ICLR 2024
• Journal reviewing: ACM TORS

Publication

• Adaptive Axes: A Pipeline for In-domain Social Stereotype Analysis (EMNLP 2024)

  Qingcheng Zeng, Mingyu Jin, Rob Voigt

• TrustAgent: Towards Safe and Trustworthy LLM-based Agents through Agent Constitution (EMNLP Findings 2024)

  Wenyue Hua, Xianjun Yang, Mingyu Jin, Wei Cheng, Ruixiang Tang, Yongfeng Zhang

• ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction (COLM 2024)

  Mingyu Jin, Haochen Xue, Zhenting Wang, Boming Kang, Ruosong Ye, Kaixiong Zhou, Mengnan Du, Yongfeng Zhang

• Target-driven Attack for Large Language Models (ECAI 2024)

  Chong Zhang, Mingyu Jin, Dong Shu, Taowen Wang, Dongfang Liu, Jinbo Jin

• The Impact of Reasoning Step Length on Large Language Models (ACL Findings 2024)

  Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du

• MathAttack: Attacking Large Language Models towards Math Solving Ability (AAAI 2024)

  Zihao Zhou, Qiufeng Wang, Mingyu Jin, Jie Yao, Jianan Ye, Wei Liu, Wei Wang, Xiaowei Huang, Kaizhu Huang

• Knowledge Graph Large Language Model (KG-LLM) for Link Prediction (ACML 2024)

  Dong Shu, Tianle Chen, Mingyu Jin, Chong Zhang, Mengnan Du, Yongfeng Zhang

Recent Research Project and Research Framework

🌟 means equal contributor

Explainability and Trustworthy of Large Language Model

• Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities

  Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Shuhang Lin, Mingyu Jin, Haochen Xue, Zelong Li, JinDong Wang, Yongfeng Zhang

• The impact of reasoning step length on large language models

  Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du

• Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?

  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

Security

• MathAttack: Attacking Large Language Models Towards Math Solving Ability

  Zihao Zhou, Qiufeng Wang, Mingyu Jin, Jie Yao, Jianan Ye, Wei Liu, Wei Wang, Xiaowei Huang, Kaizhu Huang

• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

  Qingcheng Zeng, Mingyu Jin, Qinkai Yu, Zhenting Wang, Wenyue Hua, Zihao Zhou, Guangyan Sun, Yanda Meng, Shiqing Ma, Qifan Wang, Felix Juefei-Xu, Kaize Ding, Fan Yang, Ruixiang Tang, Yongfeng Zhang

• Towards Imperceptible Backdoor Attack in Self-supervised Learning

  Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma

Interest in Life

• 三国杀
• Basketball
• Travel

Powered by Jekyll and Minimal Light theme.