Transparent AI: The Case for Interpretability and Explainability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ramachandram, Dhanesh, Joshi, Himanshu, Zhu, Judy, Gandhi, Dhari, Hartman, Lucas, Raval, Ananya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909713812160512
author Ramachandram, Dhanesh
Joshi, Himanshu
Zhu, Judy
Gandhi, Dhari
Hartman, Lucas
Raval, Ananya
author_facet Ramachandram, Dhanesh
Joshi, Himanshu
Zhu, Judy
Gandhi, Dhari
Hartman, Lucas
Raval, Ananya
contents As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI research and enabling industry adoption, we present key insights and lessons learned from practical interpretability applications across diverse domains. This paper offers actionable strategies and implementation guidance tailored to organizations at varying stages of AI maturity, emphasizing the integration of interpretability as a core design principle rather than a retrospective add-on.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23535
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transparent AI: The Case for Interpretability and Explainability
Ramachandram, Dhanesh
Joshi, Himanshu
Zhu, Judy
Gandhi, Dhari
Hartman, Lucas
Raval, Ananya
Machine Learning
Artificial Intelligence
Computers and Society
As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI research and enabling industry adoption, we present key insights and lessons learned from practical interpretability applications across diverse domains. This paper offers actionable strategies and implementation guidance tailored to organizations at varying stages of AI maturity, emphasizing the integration of interpretability as a core design principle rather than a retrospective add-on.
title Transparent AI: The Case for Interpretability and Explainability
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2507.23535