Using Captum to Explain Generative Language Models

Vivek Miglani, Aobo Yang, Aram H. Markosyan, Diego Garcia-Olano, Narine Kokhlikyan
12/9/2023
cs.CLcs.AI

No confident code implementation found for this 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 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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{miglani2023using,
  title  = {Using Captum to Explain Generative Language Models},
  author = {Vivek Miglani and Aobo Yang and Aram H. Markosyan and Diego Garcia-Olano and Narine Kokhlikyan},
  year   = {2023},
  eprint = {2312.05491},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.05491v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.05491.svg)](https://codeofpaper.com/paper/2312.05491)

Discussion