Weiyan Shi

3
Papers
8
Total Citations

Papers (3)

LLMs Encode Harmfulness and Refusal Separately

NeurIPS 2025arXiv
8
citations

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

CVPR 2024
0
citations

Position: A Safe Harbor for AI Evaluation and Red Teaming

ICML 2024
0
citations