Scholar
Ashima Suvarna
Google Scholar ID: Rug0TJEAAAAJ
University of California, Los Angeles
Citations & Impact
Citations
194
H-index
7
i10-index
4
Publications
12
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Publications: AI Debate Aids Assessment of Controversial Claims (NeurIPS 2025); ModelCitizens (EMNLP Main 2025); Joint Preference Optimization (ACL Findings 2025); Preprints: ModelCitizens: Representing Community Voices in Online Safety; OpenThoughts (including OpenThinker-7B model); AI Debate Aids Assessment of Controversial Claims.
Research Experience
- Collaborates with Prof. Nanyun Peng, Prof. Kai-Wei Chang, and Prof. Tom Hartvigsen; Works on data curation with Prof. Ludwig Schmidt through datacomp.
Education
- UCLA CS PhD program (Advisor: Prof. Saadia Gabriel); Awards: UCLA Computer Science Fellowship 2024, Google Deepmind Scholarship 2021-2023 (UCLA MSCS), Mitacs Globalink Research 2019.
Background
- PhD student at UCLA CS, advised by Prof. Saadia Gabriel. Research focuses on post-training data recipes and training paradigms for improving the reasoning, alignment, and safety of LLMs.
Miscellany
- Participates in SheFrames, a crowdsourced art project celebrating womanhood; Reviewer for ICLR Tiny Papers 2024, SoCal NLP Symposium 2023, Neurips D&B 2024, COLM 2024, COLM 2025, ACL May ARR 2025; Organizer of UCLA NLP Seminar Series.
