Author

Yi Liu

Observed name: Liu, Yi

Institutions: Boston University, Griffith University, City University of Hong Kong

Observed institutions: Boston University, Griffith University, City University of Hong Kong

OpenAlex ID: A5125429160

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

2026 · Liu, Yi, Chen, Zhihao, et al. · arXiv (Cornell University) · 84

Agentic memory-augmented retrieval and evidence grounding for medical question-answering tasks

2026 · Shuyue Jia, Subhrangshu Bit, et al. · International Journal of Medical Informatics · 6

Confundo: Learning to Generate Robust Poison for Practical RAG Systems

2026 · Hu, Haoyang, Jiang, Zhejun, et al. · arXiv (Cornell University) · 5

Entity-centric evaluation of large language model responses for medical question-answering tasks

2026 · Yi Liu, Vijaya B. Kolachalama · PLOS Digital Health · 1

Domain-adapted language model using reinforcement learning for various dementias

2026 · Sahana S. Kowshik, Varuna H. Jasodanand, et al. · medRxiv · 1

AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

2026 · Ding, Junchen, Dong, Jialiang, et al. · arXiv (Cornell University)

Works count: 6

Citation count: 97

H-index: 3

I10-index: 1