KIT | KIT-Bibliothek | Impressum | Datenschutz

RIXA - Explaining Artificial Intelligence in Natural Language

Becker, Maximilian ORCID iD icon 1; Vishwesh, Vishwesh 2; Birnstill, Pascal 2; Schwall, Finn 2; Wu, Sihan 3; Beyerer, Jürgen 1,2
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)
2 Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (IOSB)
3 Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

Natural language is the instinctive form of communication humans use among each other. Recently large language models have drastically improved and made natural language interfaces viable for all kinds of applications. We argue that the use of natural language is a great tool to make explainable artificial intelligence (XAI) accessible to end users. We present our concept and work in progress implementation of a new kind of XAI dashboard that uses a natural language chat. We specify 5 design goals for the dashboard and show the current state of our implementation. The natural language chat is the main form of interaction for our new dashboard. Through it the user should be able to control all important aspects of our dashboard. We also define success metrics we want to use to evaluate our work. Most importantly we want to conduct user studies because we deem them to be the best method of evaluation for end-user-centered applications.


Postprint §
DOI: 10.5445/IR/1000173986
Veröffentlicht am 09.10.2024
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 06.02.2024
Sprache Englisch
Identifikator ISBN: 979-8-3503-8165-8
ISSN: 2375-9232
KITopen-ID: 1000173986
HGF-Programm 46.23.04 (POF IV, LK 01) Engineering Security for Production Systems
Erschienen in 2023 IEEE International Conference on Data Mining Workshops (ICDMW), Shanghai, 1st-4th December 2023
Veranstaltung IEEE International Conference on Data Mining Workshop (ICDMW 2023), Shanghai, China, 01.12.2023 – 04.12.2023
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 875–884
Schlagwörter XAI, natural language explanations, interactive explanations, personalized explanations, XAI dashboard
Nachgewiesen in Dimensions
Scopus
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page