Publications

Exploring the Alignment Landscape: LLMs and Geometric Deep Models in Protein Representation

Dong Shu, Bingbing Duan, Kai Guo, Kaixiong Zhou, Jiliang Tang, and Mengnan Du. "Exploring the Alignment Landscape: LLMs and Geometric Deep Models in Protein Representation." arXiv preprint arXiv:2411.05316 (2024).
Paper | View Code

Health-llm: Personalized retrieval-augmented disease prediction system

Jin, Mingyu, Qinkai Yu, Dong Shu, Chong Zhang, Lizhou Fan, Wenyue Hua, Suiyuan Zhu et al. "Health-llm: Personalized retrieval-augmented disease prediction system." arXiv preprint arXiv:2402.00746 (2024).
Paper

AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models

Dong Shu, Mingyu Jin, Suiyuan Zhu, Beichen Wang, Zihao Zhou, Chong Zhang, and Yongfeng Zhang. "Attackeval: How to evaluate the effectiveness of jailbreak attacking on large language models." arXiv preprint arXiv:2401.09002 (2024).
Paper

When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments

Liu, Xinyi, Chong Zhang, Mingyu Jin, Zhongmou Zhang, Zhenting Wang, Dong Shu, Suiyuan Zhu, Sujian Li, Mengnan Du, and Yongfeng Zhang. "When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments."
Paper

Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI

Dong Shu, and Zhouyao Zhu. "Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI." arXiv preprint arXiv:2403.10559 (2024).
Paper

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning

Published in AAAI-25 Student Abstract (Oral Presentation), 2025

Dong Shu, and Mengnan Du. "Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning." arXiv preprint arXiv:2410.23099 (2024).
Paper | View Code

Counterfactual Explainable Incremental Prompt Attack Analysis on Large Language Models

Published in IEEE BigData Workshop, 2024

Dong Shu, Mingyu Jin, Tianle Chen, Chong Zhang, and Yongfeng Zhang. "CEIPA: Counterfactual Explainable Incremental Prompt Attack Analysis on Large Language Models." arXiv preprint arXiv:2407.09292 (2024).
Paper

Knowledge graph large language model (KG-LLM) for link prediction

Published in ACML, 2024

Dong Shu, Tianle Chen, Mingyu Jin, Chong Zhang, Mengnan Du, and Yongfeng Zhang. "Knowledge graph large language model (KG-LLM) for link prediction." arXiv preprint arXiv:2403.07311 (2024).
Paper | Website

LawLLM: Law Large Language Model for the US Legal System

Published in CIKM, 2024

Dong Shu, Haoran Zhao, Xukun Liu, David Demeter, Mengnan Du, and Yongfeng Zhang. "LawLLM: Law Large Language Model for the US Legal System." In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pp. 4882-4889. 2024.
Paper | Website | View Code

Target-Driven Attack for Large Language Models

Published in ECAI, 2024

Zhang, Chong, Mingyu Jin, Dong Shu, Taowen Wang, Dongfang Liu, and Xiaobo Jin. "Target-driven Attack for Large Language Models, CCF B." In European Conference on Artificial Intelligence (ECAI), 2024. 2024.
Paper

ARIF: An Adaptive Attention-Based Cross-Modal Representation Integration Framework

Published in ICANN, 2024

Liu, Chengzhi, Zihong Luo, Yifei Bi, Zile Huang, Dong Shu, Jiheng Hou, Hongchen Wang, and Kaiyu Liang. "ARIF: An Adaptive Attention-Based Cross-Modal Representation Integration Framework." In International Conference on Artificial Neural Networks, pp. 3-18. Cham: Springer Nature Switzerland, 2024.
Paper

The Impact of Reasoning Step Length on Large Language Models

Published in ACL Finding, 2024

Jin, Mingyu, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, and Mengnan Du. "The impact of reasoning step length on large language models." arXiv preprint arXiv:2401.04925 (2024).
Paper | View Code

Assessing prompt injection risks in 200+ custom gpts

Published in ICLR Workshop, 2024

Yu, Jiahao, Yuhang Wu, Dong Shu, Mingyu Jin, Sabrina Yang, and Xinyu Xing. "Assessing prompt injection risks in 200+ custom gpts." arXiv preprint arXiv:2311.11538 (2023).
Paper | View Code