Yucheng Shi

Yucheng Shi - 史淯城

I am a fourth-year Ph.D. Candidate at the University of Georgia, under the mentorship of Prof. Ninghao Liu. My research lies at the critical intersection of Data-centric AI and Responsible AI. My work focuses on improving input data quality, at training/inference phases, to boost the performance, interpretability, and safety of models. Currently, I am exploring methods to generate synthetic data for large foundation models to enhance their performance and reliability. My specific areas of research include:

Synthetic Data: Self-synthesized multimodal data, Zero-shot image purification.
Retrieval Augmented Generation: Retrieval Augmented Editing, Medical RAG.
Explainability and its utilization: XAI Usage with LLMs, Explanation of Deep Visual Neurons, XAI with Time Series.
Medical Foundation Models: Radiology Llama 70B Post-training (tech report).

UGA | LinkedIn | Google Scholar | GitHub | CV

Publications

*Equal contribution.

Synthetic Data Generation

	Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li, Ninghao Liu. (ICLR), International Conference on Learning Representations, 2025. [Paper] [Code] [Model]
	Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu. (NeurIPS), Conference on Neural Information Processing Systems, 2023. [Paper] [Code]

Retrieval Augmented Generation

	SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering? Yucheng Shi, Tianze Yang, Canyu Chen, Quanzheng Li, Tianming Liu, Xiang Li, Ninghao Liu. (arXiv), 2025. [Paper]
	Retrieval-Enhanced Knowledge Editing for Multi-Hop Question Answering in Language Models Yucheng Shi, Qiaoyu Tan, Xuansheng Wu, Shaochen Zhong, Kaixiong Zhou, Ninghao Liu. (CIKM), ACM International Conference on Information and Knowledge Management, 2024. [Paper] [Code] [Slides]
	MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering Yucheng Shi^, Shaochen Xu^, Tianze Yang^, Zhengliang Liu, Tianming Liu, Quanzheng Li, Xiang Li, Ninghao Liu. (AMIA)*, American Medical Informatics Association Annual Symposium, 2024. [Paper] [Code] [Distinguished Paper Award]
	MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations Shaochen Zhong, Yifan Lu, Lize Shao, Bhargav Bhushanam, Xiaocong Du, Yixin Wan, Yucheng Shi, Daochen Zha, Yiwei Wang, Ninghao Liu, Kaixiong Zhou, Shuai Xu, Kai-Wei Chang, Louis Feng, Vipin Chaudhary, Xia Hu (ICLR), International Conference on Learning Representations, 2025. [Paper]

Medical Foundation Models

	ECHOPulse: ECG Controlled Echocardio-gram Video Generation Yiwei Li, Sekeun Kim, Zihao Wu, Hanqi Jiang, Yi Pan, Pengfei Jin, Sifan Song, Yucheng Shi, Xiaowei Yu, Tianze Yang, Tianming Liu, Quanzheng Li, Xiang Li (ICLR), International Conference on Learning Representations, 2025. [Paper]
	MGH Radiology Llama: A Llama 3 70B Model for Radiology Yucheng Shi, Peng Shu, Zhengliang Liu, Zihao Wu, Quanzheng Li, Tianming Liu, Ninghao Liu, Xiang Li (Preprints), Tech Report, 2024. [Paper]

Graph Self-supervised Learning

	GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction Yucheng Shi, Yushun Dong, Qiaoyu Tan, Jundong Li, Ninghao Liu. (CIKM), ACM International Conference on Information and Knowledge Management, 2023. [Paper] [Code]
	ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning Yucheng Shi, Kaixiong Zhou, Ninghao Liu. (ECML-PKDD), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023. [Paper] [Code]

Explainability and its utilization

	Towards Trustworthy GUI Agents: A Survey Yucheng Shi, Yucheng Shi, Wenhao Yu, Wenlin Yao, Wenhu Chen, Ninghao Liu (Preprints) [Paper] [Code]
	CORTEX: Concept-Oriented Token Explanation in Vector-Quantized Generative Model Tianze Yang^, Yucheng Shi^, Mengnan Du, Xuansheng Wu, Qiaoyu Tan, Jin Sun, Ninghao Liu (Preprints) [Paper]
	Quantifying Multilingual Performance of Large Language Models Across Languages Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ali Payani, Ninghao Liu, Mengnan Du. (AAAI), Association for the Advancement of Artificial Intelligence, 2025. [Paper] [Code]
	Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era Xuansheng Wu^, Haiyan Zhao^, Yaochen Zhu^, Yucheng Shi^, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu. (Preprints) [Paper] [Code]
	Automated Natural Language Explanation of Deep Visual Neurons with Large Models Chenxu Zhao, Wei Qian, Yucheng Shi, Mengdi Huai, Ninghao Liu. (AAAI), Association for the Advancement of Artificial Intelligence, Student abstract, 2024. [Paper]
	ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs Yucheng Shi^, Hehuan Ma^, Wenliang Zhong^, Qiaoyu Tan, Gengchen Mai, Xiang Li, Tianming Liu, Junzhou Huang. (ICDMW)*, International Workshop on Learning with Knowledge Graphs @ ICDM2023, 2023. [Paper] [Code]
	Interpretation of Time-Series Deep Models: A Survey Ziqi Zhao^, Yucheng Shi^, Shushan Wu^, Fan Yang, Wenzhan Song, Ninghao Liu. (Preprints)* [Paper] [Code]