Model Science: getting serious about verification, explanation and control of AI systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Biecek, Przemyslaw, Samek, Wojciech
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915466543366144
author Biecek, Przemyslaw
Samek, Wojciech
author_facet Biecek, Przemyslaw
Samek, Wojciech
contents The growing adoption of foundation models calls for a paradigm shift from Data Science to Model Science. Unlike data-centric approaches, Model Science places the trained model at the core of analysis, aiming to interact, verify, explain, and control its behavior across diverse operational contexts. This paper introduces a conceptual framework for a new discipline called Model Science, along with the proposal for its four key pillars: Verification, which requires strict, context-aware evaluation protocols; Explanation, which is understood as various approaches to explore of internal model operations; Control, which integrates alignment techniques to steer model behavior; and Interface, which develops interactive and visual explanation tools to improve human calibration and decision-making. The proposed framework aims to guide the development of credible, safe, and human-aligned AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20040
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Model Science: getting serious about verification, explanation and control of AI systems
Biecek, Przemyslaw
Samek, Wojciech
Artificial Intelligence
Machine Learning
The growing adoption of foundation models calls for a paradigm shift from Data Science to Model Science. Unlike data-centric approaches, Model Science places the trained model at the core of analysis, aiming to interact, verify, explain, and control its behavior across diverse operational contexts. This paper introduces a conceptual framework for a new discipline called Model Science, along with the proposal for its four key pillars: Verification, which requires strict, context-aware evaluation protocols; Explanation, which is understood as various approaches to explore of internal model operations; Control, which integrates alignment techniques to steer model behavior; and Interface, which develops interactive and visual explanation tools to improve human calibration and decision-making. The proposed framework aims to guide the development of credible, safe, and human-aligned AI systems.
title Model Science: getting serious about verification, explanation and control of AI systems
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.20040