A Review of the Role of Causality in Developing Trustworthy AI Systems

Niloy Ganguly, Dren Fazlija, Maryam Badar, Marco Fisichella, Sandipan Sikdar +7 more
2/14/2023
cs.AI

No official code found. Best implementation: L3S/causality-for-trustworthy-ai (8 stars, last commit 2023-09-12).

Abstract

State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are difficult to interpret. This has led to efforts to improve the trustworthiness aspects of AI models. Recently, causal modeling and inference methods have emerged as powerful tools. This review aims to provide the reader with an overview of causal methods that have been developed to improve the trustworthiness of AI models. We hope that our contribution will motivate future research on causality-based solutions for trustworthy AI.

View on arXivView PDF

Code Implementations(1)

L3S/causality-for-trustworthy-aiCommunity100%

:books: Curated list for Causality and AI

80May 10, 20233 years ago
accountabilityadversarial-machine-learningauditingbiasdatasets+15 more

Similar Papers

The Importance of Causality in Decision Making: A Perspective on Recommender Systems

85% match2024

Causality from Bottom to Top: A Survey

84% match2024

On the Definition of Appropriate Trust and the Tools that Come with it

84% match2023

Is Knowledge All Large Language Models Needed for Causal Reasoning?

83% match1 repo172023

Quantifying Consistency and Information Loss for Causal Abstraction Learning

83% match1 repo42023

Discovering and Reasoning of Causality in the Hidden World with Large Language Models

83% match2024

Cite this paper

@article{ganguly2023review,
  title  = {A Review of the Role of Causality in Developing Trustworthy AI Systems},
  author = {Niloy Ganguly and Dren Fazlija and Maryam Badar and Marco Fisichella and Sandipan Sikdar and Johanna Schrader and Jonas Wallat and Koustav Rudra and Manolis Koubarakis and Gourab K. Patro and Wadhah Zai El Amri and Wolfgang Nejdl},
  year   = {2023},
  eprint = {2302.06975},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.06975v1}
}

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/2302.06975.svg)](https://codeofpaper.com/paper/2302.06975)

Discussion