What is happening
News and updates
- New research in the New Future of Work Reader examining agentic delegation failures from a user perspective
- Our new preprint, Babysitting AI Agents, examines agentic delegation failures from a user perspective. Out now on arXiv!
- New research in the New Future of Work Reader on the context AI misses while drafting in the workplace.
- The 2026 Work Trend Index is out, focusing on agents and human agency. It features our user x agent intensity framework and has been covered by Forbes, GeekWire, and other news outlets.
- Thrilled to announce that I have defended my PhD titled LLMs as Sociotechnical Actors: A Scaffolding Framework for Recovering Context Lost in Text-Only Settings. Grateful to everyone who supported this work!
- The 2025 Microsoft New Future of Work report is out and cites our Not Just My Style research.
- The PATHs paper received a Senior Area Chair Highlight award at EMNLP 2025!
- Started as a Senior Applied Scientist at Microsoft and moved to the Seattle area! I will continue working on human-agent collaboration for productivity.
- Our paper PATHs is accepted to EMNLP 2025! See you in Suzhou, China.
- LawFlow is accepted to COLM 2025! See you in Montreal.
- LawFlow, which captures lawyers’ end-to-end thought processes, is out on ArXiv!
- Gave a talk titled When AI Learns to Listen: Generative AI in the Social Sciences to high school students at the Sparkway Learning PythonAI Workshop 2024.
- Honored to be a speaker at the Women in AI and Data Science Conference 2024, discussing the impact of artifacts in LLM-generated data.
- Thrilled to be interning at the Office of Applied Research at Microsoft this fall!
- Received the 2024 AnitaB.org Advancing Inclusion Scholarship!
- Our paper Publics’ Perceptions of Legitimacy in Corporate Social Advocacy: A Computational Analysis of the Influence of Ideological Congruence is published in Public Relations Review.
- Gave a talk titled Beyond Words: Incorporating Graph Data into LLMs for Comprehensive Social System Analysis at IC2S2 2024.
- Presented Which Modality should I use? at NAACL 2024 in Mexico City! [Tweet]
- Thrilled to be interning at Microsoft Research this summer!
- Presented my recent paper on LLM-generated artifacts at Megagon Labs, along with Dongyeop Kang.
- Passed my Thesis Proposal Exam :) One more exam to go until my defense!
- Abstract Beyond Words: Incorporating Graph Data into LLMs for Comprehensive Social System Analysis selected for oral presentation at IC2S2 2024!
- Which Modality should I use — Text, Motif, or Image? Understanding Graphs with Large Language Models is accepted at NAACL 2024 Findings!
- Under the Surface: Tracking the Artifactuality of LLM-Generated Data is out on ArXiv. This paper marks my first venture as a project team lead and MinnesotaNLP’s first lab-wide project!
- New preprint at the intersection of graphs and LLMs — Which Modality should I use — Text, Motif, or Image? Understanding Graphs with Large Language Models is out on ArXiv!
- Our paper Balancing the Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer was presented at ACL 2023 Findings.
- Our work on Rebuilding Social Connection and Enhancing Advertising Effects Through the Nostalgic Appeal during the Pandemic was accepted to AEJMC 2023.
- Our work on Work In Progress: Reactions to Incivility: A Computational Approach to Measuring Affective Polarization on Twitter During the First 2020 U.S. Presidential Debate was accepted to ICA 2023.
- Our work on Publics’ Perceptions of Legitimacy in Corporate Social Advocacy: A Computational Analysis of the Influence of Ideological Congruence was accepted to ICA 2023.
- Our paper AdBERT: An Effective Few Shot Learning Framework for Aligning Tweets to Superbowl Advertisements was presented at WNUT @ COLING 2022.