Zijun Yao
4
Papers
116
Total Citations
1
Affiliations
Affiliations
Tsinghua University
Papers (4)
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
ICLR 2024arXiv
85
citations
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
NeurIPS 2025arXiv
23
citations
How do Transformers Learn Implicit Reasoning?
NeurIPS 2025arXiv
8
citations
RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
ICLR 2025arXiv
0
citations