Amir Feder
Scholar

Amir Feder

Google Scholar ID: ERwoPLIAAAAJ
Hebrew University, Google
language modelscausalitymachine learningcomputational social science
Citations & Impact
All-time
Citations
3,130
 
H-index
22
 
i10-index
29
 
Publications
20
 
Co-authors
12
list available
Resume (English only)
Academic Achievements
  • Published 'Evaluating the Moral Beliefs Encoded in LLMs' at NeurIPS 2023 (Spotlight).
  • Published 'Data Augmentations for Improved (Large) Language Model Generalization' at NeurIPS 2023.
  • Published 'On Calibration and Out-of-domain Generalization' at NeurIPS 2021.
  • Published 'CausaLM: Causal model explanation through counterfactual language models' in Computational Linguistics (2021).
  • Co-authored the survey 'Causal Inference in Natural Language Processing' in TACL 2022.
  • Delivered the tutorial 'Causal Inference for NLP' at EMNLP 2022.
  • Co-organized the First Workshop on NLP and Causal Inference (CI+NLP) at EMNLP 2021.
  • Advising PhD students including Zach Bamberger (Technion), Shimon Nowik (Hebrew U), and Itamar Trainin (Hebrew U).