Scholar
Bingbing Wen
Google Scholar ID: Jt0E6FEAAAAJ
University of Washington
Citations & Impact
Citations
145
H-index
8
i10-index
7
Publications
17
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - Published paper: MARVEL: Modular Abstention for Reliable and Versatile Expert LLMs
- - Published paper: AutoScale-Automatic Prediction of Compute-optimal Data Composition for Training LLMs
- - Published paper: Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
- - Published paper: Know Your Limits: A Survey of Abstention in Large Language Models
- - Published paper: Characterizing LLM Abstention Behavior in Science QA with Context Perturbations
Research Experience
- - Conducted research internships at Apple, Microsoft Cloud AI, and OPPO Research, exploring challenges in building large-scale AI systems
- - Closely collaborates with the Allen Institute for AI
- - Actively mentors undergraduate and master students in developing and carrying out research projects
Education
- - Ph.D. in Information Science (Natural Language Processing), University of Washington, Advisors: Prof. Bill Howe and Prof. Lucy Lu Wang
- - M.S. in Computational Science & Engineering (Artificial Intelligence), University of Hong Kong
- - B.S. in Control Science & Engineering (Robotics), Zhejiang University
Background
- - Research Interests: Data Efficiency, Model Efficiency, Evaluation Methods
- - Professional Field: Natural Language Processing, Artificial Intelligence
- - Bio: PhD student at the University of Washington, focusing on optimizing data mixtures and designing fine-grained preference signals, exploring modular and adaptive architectures, and designing abstention and confidence-based evaluation frameworks.
