Scholar
Debarati Das
Google Scholar ID: NpoVjbMAAAAJ
Ph.D Computer Science, University of Minnesota, Twin Cities
Citations & Impact
Citations
160
H-index
8
i10-index
6
Publications
20
Co-authors
8
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Paper 'PATHs' accepted to EMNLP 2025; 'LawFlow' accepted to COLM 2025 and out on ArXiv; received the 2024 AnitaB.org Advancing Inclusion scholarship; published a paper on publics’ perceptions of legitimacy in corporate social advocacy in Public Relations Review; presented a paper on understanding graphs with large language models at NAACL 2024.
Research Experience
- Currently a Senior Applied Scientist at Microsoft as part of the IDEAS Research group led by Scott Counts, working on measuring and steering the impact of Generative AI on Productivity. Interned at Microsoft Research and 3M R&D previously.
Education
- During her PhD, she was a member of the Minnesota NLP group led by Prof. Dongyeop Kang and co-supervised by Prof. Jaideep Srivastava, who leads the Data Mining and Research Group (DMR) at the University of Minnesota Twin Cities. Previously interned at Microsoft Research and 3M R&D. Earned her Master’s degree at the University of Minnesota Twin Cities, where she worked on applying NLP to online social media analysis before completing her PhD.
Background
- Research interests lie at the intersection of natural language processing and computational social science, with a focus on designing and evaluating large language models (LLMs) in human-centered, high-stakes contexts. Particularly interested in how LLMs can support expert decision-making by participating in structured and interpretable workflows. Additionally, works on characterizing the generative behavior of LLMs, with an emphasis on understanding how their outputs align (or misalign) with users' values, expectations, and goals.
Miscellany
- Gave a talk titled 'When AI learns to Listen: Generative AI in the Social Sciences' to high school students for the Sparkway Learning PythonAI Workshop 2024; spoke at the Women in AI and DS Conference 2024 about the impact of artifacts in LLM-generated data.
