I’m an assistant professor at the University of Utah’s Kahlert School of Computing, where I co-lead UtahNLP and run the ANANAS research group.
I study how to build AI technologies that support human decision-making, communication, and creativity. I identify where such assistance is valuable and develop benchmarks to test how reliably AI performs on related tasks involving language, images, and audio. I’m increasingly focused on collaboration with agents and applications in higher education through my role as an RAI faculty fellow.
A central thread of my work also explores how to translate what AI models “know” into reasoning that people can follow and act on. My most notable contributions in this area examine whether a model’s verbal explanations are faithful to its internal computations.
News
| Jun 2025 | Having built hard reasoning-over-text benchmarks the "old-fashioned" way (with crowdworkers), we had to ask: what if we used LLMs instead? Answer in the new preprint: we'd get an easier benchmark. |
| May 2025 | I gave a keynote at Repl4NLP @ NAACL on measuring faithfulness of verbalized reasoning: If You Want Reasoning, Look Inside. |
| Feb 2025 | We released a preprint on measuring faithfulness of verbalized reasoning grounded in model iternals. |
| Sep 2024 | Our work on application-grounded evaluations of explanations in NLP is accepted to EMNLP Findings! |
| Jun 2024 | Our work on measuring chain-of-thought faithfulness is accepted to TMLR. |
| Jun 2024 | I prepared a session on data influence for NAACL Tutorial: Explanations in the Era of Large Language Models. |