Juanzi Li

5

Papers

150

Total Citations

Papers (5)

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

NeurIPS 2025arXiv

How do Transformers Learn Implicit Reasoning?

EventSum: A Large-Scale Event-Centric Summarization Dataset for Chinese Multi-News Documents