Wenhu Chen

Assistant Professor at the University of Waterloo working on natural language understanding, machine reading comprehension, and language model safety. Research interests include question answering, commonsense reasoning, and adversarial robustness of NLP systems.

Sources in this wiki

• On the Risk of Misinformation Pollution with Large Language Models

Topics

• Question Answering Systems, LLM Safety and Adversarial Robustness, Synthetic Text Generation

Notes

Active researcher in the NLP community with focus on understanding and mitigating vulnerabilities in language models.