Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Projects › KIWIS - Entwicklung eines integrierten Kl-gestützten Wissensmanagementsystems zur Optimierung der Produktion von Elektrofahrzeugkomponenten und Marktanalysen im Automotive-Bereich

Project

KIWIS - Entwicklung eines integrierten Kl-gestützten Wissensmanagementsystems zur Optimierung der Produktion von Elektrofahrzeugkomponenten und Marktanalysen im Automotive-Bereich

Ongoing

Details

Project data

Title
KIWIS - Entwicklung eines integrierten Kl-gestützten Wissensmanagementsystems zur Optimierung der Produktion von Elektrofahrzeugkomponenten und Marktanalysen im Automotive-Bereich
Project leader
Department
Person involved
Start date
2025-03-01
End date
2028-02-28
Category
Grundlagenforschung

Project description

Acronym
KIWIS
URL
Description

The project is a collaboration between the BMW Group and the University of Bamberg, aimed at developing an AI-driven knowledge management system that integrates agentic large language models (LLMs) with modular AI systems. The goal is to improve knowledge access for employees by combining various data sources, while ensuring factual consistency and reducing hallucinations.

By leveraging modular AI models, the agentic LLM activates relevant knowledge modules based on user queries using topic modeling and retrieval-augmented generation (RAG). This modular approach enables efficient processing of different data types and representations, delivering accurate and context-based answers.

The University of Bamberg focuses on reducing hallucinations in LLMs, developing methods to activate AI modules using topic modeling and RAG, and applying cognitive science approaches to design explainable results. The project explores use cases in electric vehicle manufacturing and market analysis, utilizing a chat-based dashboard to facilitate natural interaction with the knowledge base.

The aim is to create a user-friendly and efficient system that enhances transparency and trust, improving knowledge access and interaction for employees in the fields of manufacturing and market analysis.

Area of research
Computer Science
Cognitive Systems
Explainability
Mitigating Hallucinations of Large Language Models
Agentic Large Language Models

Grants

Donor of third party fundsProgramSubsidy amountFunding periodFunding CodeURL
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und EnergieBayVFP Förderlinie Digitalisierung325,006.00 €01.03.2025-29.02.2028DIK0700/02https://www.foerderdatenbank.de/FDB/Content/DE/Foerderprogramm/Land/Bayern/verbundforschungsprogramm-bayvfp-digitalisierung.html

Partnerships

Project partnersProject nameKind of partnership
BMW GroupKIWISVerbundpartner

Publications

Permalink: https://fis.uni-bamberg.de/handle/uniba/105466 · Data as JSON

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.