I am a postdoctoral research associate at the Center for Information Technology Policy (CITP) and the Polaris Lab at Princeton University. I received my Dr. Sc. in Spring 2024 from ETH Zurich for my dissertation on on data-centric automated fact-checking.
My current research centers on legal NLP and AI to support public defenders and improve access to justice. We are developing AI tools to provide computational assistance for public defenders and make their work more effective. In parallel, we are conducting interviews with public defenders across the US to understand their perspectives on AI. Our goal is to identify opportunities and challenges around AI and its implications on the day-to-day work of public defenders, and especially what would be good use cases to develop AI tools for.
More broadly, my research aims to develop NLP and AI that serve public agencies and strengthen the public sector.
Aligning Large Language Models with Diverse Political Viewpoints, with Philine Widmer, Eunjung Cho, Caglar Gulcehre and Elliott Ash, EMNLP 2024
Environmental Claim Detection, with Nicolas Webersinke, Julia Bingler, Mathias Kraus and Markus Leippold (ACL 2023)
Revisiting Automated Topic Model Evaluation with Large Language Models, with Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan and Elliott Ash (EMNLP 2023)
The Choice of Textual Knowledge Base in Automated Claim Checking, with Boya Zhang and Elliott Ash (ACM Journal of Data and Information Quality, 2023)
Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data , with Maria Antoniak and Elliott Ash (4th Workshop of Narrative Understanding, 2022)
Evidence Selection as a Token-Level Prediction Task (Fourth Workshop on Fact Extraction and VERification, 2021)
e-FEVER: Explanations and Summaries for Automated Fact Checking, with Elliott Ash (Truth and Trust Online, 2020)
Exploiting Evidence Enhancement for the FEVER Shared Task, with Günter Neumann (Second Workshop on Fact Extraction and VERification, 2019)