Work

Using Captum to Explain Generative Language Models

Year: 2023

Type: conference-paper

Abstract: 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 1 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.

Source: Workshop for NLP Open Source Software (NLP-OSS)

DOI: 10.18653/v1/2023.nlposs-1.19

Authors: Vivek Miglani, Aobo Yang, Aram Markosyan, Diego Garcia-Olano, Narine Kokhlikyan

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4389524014

FWCI: 5.554

Cites: 19

Cited by: 49

Related to: 10