Junyuan Hong

机构：The University of Texas at Austin · ORCID：0000-0002-5718-5187

发表论文 51 篇 · 总被引 346 次 · h-index 10

代表论文

• LLM-PBE: Assessing Data Privacy in Large Language Models (2024 · Proceedings of the VLDB Endowment · 被引 33)
• MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models (2025 · 被引 19)
• International Workshop on Federated Learning for Distributed Data Mining (2023 · 被引 10)
• Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk (2024 · 被引 9)
• Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark (2024 · arXiv (Cornell University) · 被引 7)
• DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer (2023 · arXiv (Cornell University) · 被引 5)