The paper introduces new features in the Captum library for model explainability in PyTorch, specifically designed for analyzing generative language models. It provides an overview of the functionalities and example applications for understanding learned associations in these models.

https://arxiv.org/abs//2312.05491

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers