370 citations · 752 across the 68 of their papers we have counts for
4 papers · 1 filter
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
Mengru Wang, Zhenqian Xu, Junfeng Fang +4
Large Language Models (LLMs) can acquire unintended biases from seemingly benign training data even without explicit cues or malicious content. Existing methods struggle to detect…
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Yixin Ou, Yunzhi Yao, Ningyu Zhang +5
Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly ho…
Newton-Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
Lingbing Guo, Weiqing Wang, Zhuo Chen +5
Reasoning system dynamics is one of the most important analytical approaches for many scientific studies. With the initial state of a system as input, the recent graph neural netwo…
Domain-Agnostic Molecular Generation with Chemical Feedback
Yin Fang, Ningyu Zhang, Zhuo Chen +3
The generation of molecules with desired properties has become increasingly popular, revolutionizing the way scientists design molecular structures and providing valuable support f…