Aram Markosyan


2023

pdf
Using Captum to Explain Generative Language Models
Vivek Miglani | Aobo Yang | Aram Markosyan | Diego Garcia-Olano | Narine Kokhlikyan
Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)

Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users’ understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.