EU Open Research Repository

How to submit Join with your EU project
Research and Innovation
Published August 1, 2024 | Version camera ready
Conference paper Open

Exploration of core concepts required for mid- and domain-level ontology development to facilitate explainable-AI-readiness of data and models

Creators

  • 1. ROR icon Norwegian University of Life Sciences
  • 2. ROR icon Daresbury Laboratory
  • 3. ROR icon Institute for Applied Systems Technology Bremen
  • 4. ROR icon Helmholtz-Zentrum Hereon
  • 5. ROR icon Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
  • 6. Université de Technologie Tarbes Occitanie Pyrénées
  • 7. ROR icon University of Stuttgart

Description

This position paper reports on the initial discussions within the Knowledge Graph Alliance's working group on explainable-AI-ready data and metadata principles, which was created in March 2024. At present, we are taking initial steps toward capturing core concepts related to explanation, grounding, reliance, and trust; the scope also extends to potential dual notions such as explainability, verifiability/reproducibility, reliability, and trustworthiness. These initial steps consist in reviewing core concepts as they are discussed in the literature and exploring what could be practically useful definitions of these most central concepts. One of the conclusions is that the metadata standards will need to be suitable for documenting three kinds of grounding: Grounding of knowledge, grounding of reliance, and grounding of trust. Pre-existing metadata standards at the mid and domain level are presently undergoing a redesign in order to become more modular, computationally tractable, intelligible to humans, and adjustable, which will be needed as we continue our work toward actionable recommendations. The development of this system of lite (OWL 2 EL) ontologies, called MSO-EM: Ontologies for modelling, simulation, optimization (MSO) and epistemic metadata (EM), is carried out on a public repository.

Files

DAO-XAI_explainable-ai-readiness_camera-ready_2024-08-01.pdf

Files (642.7 kB)

Additional details

Funding

European Commission
AI4Work – Human-centric Digital Twin Approaches to Trustworthy AI and Robotics for Improved Working Conditions 101135990
European Commission
BatCAT – Battery Cell Assembly Twin 101137725
European Commission
DigiPass – Harmonization of Advanced Materials Ecosystems serving strategic Innovation Markets to pave the way to a Digital Materials & Product Passport 101138510

Dates

Submitted
2024-06-14
Issued
2024-08-01
camera-ready version

Software

Repository URL
https://www.purl.org/mso-em
Programming language
Web Ontology Language
Development Status
Active