Daniel E. Ho

机构：Stanford Medicine, Stanford University · ORCID：0000-0002-2195-5469

发表论文 27 篇 · 总被引 65 次 · h-index 3

代表论文

• How well do LLMs cite relevant medical references? An evaluation framework and analyses (2024 · arXiv (Cornell University) · 被引 41)
• Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice (2025 · SSRN Electronic Journal · 被引 11)
• Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs (2025 · 被引 3)
• Extracting memorized pieces of (copyrighted) books from open-weight language models (2025 · arXiv (Cornell University) · 被引 2)
• Extracting memorized pieces of (copyrighted) books from open-weight language models (2025 · SSRN Electronic Journal · 被引 2)
• Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research (2024 · arXiv (Cornell University) · 被引 2)