Scholar
Yihuai Hong
Google Scholar ID: 4fvIAPsAAAAJ
PhD student in New York University
Citations & Impact
Citations
69
H-index
4
i10-index
3
Publications
7
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- NeurIPS 2025: First-author paper 'The Rise of Parameter Specialization for Knowledge Storage in Large Language Models' accepted; awarded NeurIPS 2025 Scholar Award
- EMNLP 2025 Main: First-author paper 'Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces' and one co-authored paper accepted
- ACL 2025 Findings: First-author paper 'The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction' accepted
- EMNLP 2024 Main: Two first-author papers accepted: 'Dissecting Fine-Tuning Unlearning in Large Language Models' and 'Interpretability-based Tailoblack Knowledge Editing in Transformers'
- AAAI 2024 main track: First paper accepted; awarded AAAI-24 Student Scholarship
- Developed the first-ever parametric LLM unlearning benchmark
