Xiaoni Duan is a PhD candidate at Purdue Computer Science Department, advised by Prof. Ming Yin. Her research lies in HCI, human-centered NLP, LLMs, and crowdsourcing. She has been working on improving the quality and mitigating biases in data annotations through both Machine Learning methods and empirical studies. She currently working on understanding and improving the alignment of Language Models for subjective tasks.

HCI, LLM, Crowdsourcing, data mining