Xiang Lorraine Li is an assistant professor in the Department of Computer Science at the University of Pittsburgh. Before joining Pitt, she worked as a young investigator with the Mosaic team at AI2. Previously, she defended her Ph.D. in Computer Science from UMass Amherst in August 2022, working with Andrew McCallum. She obtained an M.S. in Computer Science from The University of Chicago while conducting research at TTIC. Her research is at the intersection of natural language processing, commonsense reasoning, knowledge representation, and machine learning. She regularly serves on program committees and workshop organizers in the NLP and ML fields, such as ICLR, ICML, NeurIPS, ACL, EMNLP, NAACL, ARR etc.
Faith and Fate: Limits of Transformers on Compositionality (NeurIPS 2021 Spotlight)
A Systematic Investigation of Commonsense Knowledge in Large Language Models (EMNLP 2022)
Smoothing the Geometry of Probabilistic Box Embeddings. (ICLR 2019 Spotlight)
The intersection of NLP, commonsense reasoning, knowledge representation, and ML. More specifically, I'm interested in designing models powered by background knowledge to enhance model robustness and safety. To this end, I've worked on analyzing model behavior, designing evaluation methods, and proposing new model structures.