Hi! I'm Theodora Worledge, a computer science PhD student at Stanford advised by the wonderful Carlos Guestrin. I am supported by the NSF GRFP Fellowship.
I care about making ML models reliable and trustworthy. I'm particularly interested in equipping users with interpretability tools to verify outputs as model capabilities scale. Recently, I've been thinking about attributions for language model outputs.
Previously, I graduated with a BA in computer science from UC Berkeley. I am very fortunate to have worked with Esther Rolf and Ben Recht during my time there.
I often go by Teddi :)
The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations
Theodora Worledge, Tatsunori Hashimoto, Carlos Guestrin. Arxiv Preprint, 2024.
Unifying Corroborative and Contributive Attributions in Large Language Models
Theodora Worledge*, Judy Hanwen Shen*, Nicole Meister, Caleb Winston, Carlos Guestrin. SaTML, 2024.
Representation matters: Assessing the importance of subgroup allocations in training data
Esther Rolf, Theodora Worledge, Benjamin Recht, Michael I. Jordan. ICML, 2021.
My Google scholar profile is here.
The Starry Night & A Neural Algorithm of Artistic Style • 2021
