Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Binkyte, Ruta, Sheth, Ivaxi, Jin, Zhijing, Havaei, Mohammad, Schölkopf, Bernhard, Fritz, Mario
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911510171746304
author Binkyte, Ruta
Sheth, Ivaxi
Jin, Zhijing
Havaei, Mohammad
Schölkopf, Bernhard
Fritz, Mario
author_facet Binkyte, Ruta
Sheth, Ivaxi
Jin, Zhijing
Havaei, Mohammad
Schölkopf, Bernhard
Fritz, Mario
contents Ensuring trustworthiness in machine learning (ML) systems is crucial as they become increasingly embedded in high-stakes domains. This paper advocates for integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML, including fairness, privacy, robustness, accuracy, and explainability. While these objectives should ideally be satisfied simultaneously, they are often addressed in isolation, leading to conflicts and suboptimal solutions. Drawing on existing applications of causality in ML that successfully align goals such as fairness and accuracy or privacy and robustness, this paper argues that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models. Beyond highlighting these trade-offs, we examine how causality can be practically integrated into ML and foundation models, offering solutions to enhance their reliability and interpretability. Finally, we discuss the challenges, limitations, and opportunities in adopting causal frameworks, paving the way for more accountable and ethically sound AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21123
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
Binkyte, Ruta
Sheth, Ivaxi
Jin, Zhijing
Havaei, Mohammad
Schölkopf, Bernhard
Fritz, Mario
Machine Learning
Artificial Intelligence
Ensuring trustworthiness in machine learning (ML) systems is crucial as they become increasingly embedded in high-stakes domains. This paper advocates for integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML, including fairness, privacy, robustness, accuracy, and explainability. While these objectives should ideally be satisfied simultaneously, they are often addressed in isolation, leading to conflicts and suboptimal solutions. Drawing on existing applications of causality in ML that successfully align goals such as fairness and accuracy or privacy and robustness, this paper argues that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models. Beyond highlighting these trade-offs, we examine how causality can be practically integrated into ML and foundation models, offering solutions to enhance their reliability and interpretability. Finally, we discuss the challenges, limitations, and opportunities in adopting causal frameworks, paving the way for more accountable and ethically sound AI systems.
title Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.21123