Research

You can also find all my papers at my Google Scholar profile.

Publications

• Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

  Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith

  The Thirteenth International Conference on Learning Representations, 2025

  [PDF] [Blog Post]

Preprints

• Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

  Shengyuan Hu, Neil Kale, Pratiksha Thaker, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith

  Preprint, 2025

  [PDF]
• BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap

  Shengyuan Hu, Neil Kale, Pratiksha Thaker, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith

  Preprint, 2025

  [PDF]