Mor Geva

llm-interp-tau. Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University

lm-debugger. The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.

ff-layers. The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. EMNLP, 2021.

DocQN. Author implementation of "Learning to Search in Long Documents Using Document Structure" (Mor Geva and Jonathan Berant, 2018)

annotator_bias. The accompanying code for "Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets." (Mor Geva, Yoav Goldberg and Jonathan Berant, 2019)

qdmr-based-question-generation. The official code of TACL 2022, "Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition".

bionit. Python