HAPPI - Human-aware PGMs and Probabilistic Inference via Lifted Model Reconciliation (HAPPI)
Basic data for this project
Type of project: Individual project
Duration at the University of Münster: 15/03/2024 - 31/12/2026
Description
Bei diesem Projekt geht es darum, die Kommunikation zwischen KI-Systemen und Menschen zu verbessern. In KI-basierten Systemen werden häufig Modelle aus Daten gelernt. Diese Modelle können zwar auch Wissen von Expertinnen und Experten beinhalten, sind aber häufig durch die gelernten Informationen aus den Daten nicht mehr einfach zu erklären. In dem Projekt wird dort angesetzt, indem Methoden erforscht werden, wie solche gelernten Modelle mit den Erwartungen von Expertinnen und Experten in Übereinstimmung gebracht werden können und Mensch und System sich gegenseitig ihre Wissenslücken erklären können. Auf lange Sicht sollen diese Systeme zum Beispiel in Medizin oder Geisteswissenschaften ihre Vorschläge erklären können.
Keywords: AI systems; explainability; probabilistic graphical models
Website of the project: https://www.uni-muenster.de/Informatik.AGBraun/en/research/projects/happi.html
Funding identifier: 005-2401-0004
Funder / funding scheme:
- MKW - Förderlinie „Künstliche Intelligenz/Maschinelles Lernen“ - KI-Starter
Project management at the University of Münster
| Braun, Tanya |
Applicants from the University of Münster
| Braun, Tanya |
Research associates from the University of Münster
| Speller, Jan |
Publications of the University of Münster resulting from the project
Luttermann, Malte; Speller, Jan; Gehrke, Marcel; Braun, Tanya; Möller, Ralf; Hartwig, Mattis (2025) In: Kwok, James (eds.), IJCAI-25 Proceedings of the 34th International Joint Conference on Artificial Intelligence, 9077-9085. Montreal: / IJCAI Organization. doi:10.24963/ijcai.2025/1009 Research article in edited proceedings (conference) | Peer reviewed | Published | |
Speller, Jan; Luttermann, Malte; Gehrke, Marcel; Braun, Tanya (2025) In: Lynce, I.; et al. (eds.), ECAI-25 Proceedings of the 28th European Conference on Artificial Intelligence, 5051-5058. Online: IOS Press. doi:10.3233/FAIA251420 Research article in edited proceedings (conference) | Peer reviewed | Published | |
Speller, Jan; Luttermann, Malte; Gehrke, Marcel; Braun, Tanya (2025) In: Melzer, Sylvia; Peukert, Hagen; Thiemann, Stefan; Bender, Magnus; Özçep, Özgür L.; Russwinkel, Nele; Sauerwald, Kai; Wolter, Diedrich (eds.), Proceedings of the Joint Workshop on Humanities-Centred Artificial Intelligence and Formal & Cognitive Reasoning
co-located with 48th German Conference on Artificial Intelligence. CEUR-WS. Research article in digital collection (conference) | Peer reviewed | Published |
Talks about the project
| Inducing Comparability of Factorised Probability Distributions Speller, Jan; Luttermann, Malte; Gehrke, Marcel; Braun, Tanya (19/03/2026) 3rd Logic and AI Meet-up, Hagen Type of talk: scientific Talk | |
| Compression versus Accuracy: A Hierarchy of Lifted Models Speller, Jan; Luttermann, Malte; Gehrke, Marcel; Braun, Tanya (29/10/2025) 28th European Conference on Artificial Intelligence (ECAI 2025), Bologna Type of talk: scientific Talk | |
| Towards Explainability of Approximate Lifted Model Construction: A Geometric Perspective Speller, Jan (16/09/2025) Joint Workshop on Humanities-Centred Artificial Intelligence and Formal & Cognitive Reasoning co-located with 48th…, Potsdam Type of talk: scientific Talk | |
| What Can Explainability Mean for Probabilistic Inference? Braun, Tanya (27/06/2024) sAIOnARA 2024 (Conference on Shaping Trustworthy AI: Opportunities, Innovation, and Achievements for Reliable…, Bielefeld Type of talk: scientific Talk |