Sarah Wiegreffe
Scholar

Sarah Wiegreffe

Google Scholar ID: YoR3IugAAAAJ
University of Maryland
natural language processingmachine learninginterpretability
Citations & Impact
All-time
Citations
5,560
 
H-index
14
 
i10-index
16
 
Publications
20
 
Co-authors
26
list available
Resume (English only)
Academic Achievements
  • 2025: Mechanistic Interpretability Benchmark (MIB) accepted to ICML 2025; organizing the Actionable Interpretability Workshop at ICML
  • 2025: Two papers accepted to ICLR 2025, one as a spotlight
  • 2024: Selected as a Rising Star in Machine Learning
  • 2024: Selected as a Rising Star in Generative AI
  • 2024: Paper on taxonomy for model noncompliance accepted to NeurIPS 2024 Datasets and Benchmarks
  • 2024: Recognized as an Outstanding Area Chair at EMNLP 2024
  • 2023: Self-Refine published at NeurIPS
  • 2023: Outstanding Area Chair award at ACL 2023 (top 1.5%)
  • 2023: Top reviewer at NeurIPS 2023
  • 2023: Selected as a Rising Star in EECS
  • Multiple publications and invited talks at top conferences including ACL, EMNLP, NAACL, COLM, ICLR, and NeurIPS
  • 2024: Co-taught a tutorial on 'Explanation in the Era of Large Language Models' at NAACL 2024
  • Active organizer and participant in workshops such as BlackBoxNLP on interpretability