Joonsuk Park, associate professor of computer science, published the paper "tRAG: Term-level Retrieval-Augmented Generation for Zero-shot Retrieval" in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL).

Upcoming Course for Spring 2025
Title: Applied Survival Analysis, DSST 395
Description: This course will introduce analysis strategies for time-to-event data. Topics covered will include appropriate strategies for characterization and visualization of time-to-event trends, as well as strategies for formal comparison of time-to-event trends between groups. Survival analysis is typically applied to health-related research questions, but skills gained in this course will also be applicable to other fields including environmental, business, and marketing-related research questions positioned to assess time-to-event outcomes.

Data Visualization Grant-Funding
Statistics professor Taylor Arnold and digital humanities professor Lauren Tilton recently received grant funding for two data science projects. They received a $485,000 grant from the Mellon Foundation for their Distant Viewing Toolkit project, an open-source technology for the computational analysis of visual culture. Arnold and Tilton have also received a nearly $325K grant from the National Endowment for the Humanities to support a project to build open-source software for collecting and analyzing digital images.
Faculty Highlights
Joonsuk Park, associate professor of computer science, published the paper "Return of EM: Entity-driven Answer Set Expansion for QA Evaluation" in Proceedings of the International Conference on Computational Linguistics (COLING).
Joonsuk Park, associate professor of computer science, published the paper "AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence" in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL).
Joonsuk Park, associate professor of computer science, published the paper "Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation" in the Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL).