Logo des Repositoriums

Auflistung nach Autor:in "Jilek, Christian"

1 - 3 von 3
  • Journal
    Managed Forgetting to Support Information Management and Knowledge Work
    (KI - Künstliche Intelligenz: Vol. 33, No. 1, 2019) Jilek, Christian; Runge, Yannick; Niederée, Claudia; Maus, Heiko; Tempel, Tobias; Dengel, Andreas; Frings, Christian
  • Konferenzbeitrag
    Towards Context-aware Recommender Systems for Supporting Knowledge Workers in Personal and Corporate Information Space
    (INFORMATIK 2024, 2024) Bakhshizadeh, Mahta; Jilek, Christian; Maus, Heiko; Dengel, Andreas
    Although recommender systems have been impressively progressing in many domains, their usage in supporting knowledge workers has not been explored as much as in other applications. Having the existing challenges and the recent studies addressing this novel application introduced, this paper provides a framework for integrating such systems into existing concepts and technologies for knowledge assistance. As a case study, a sample recommendation scenario according to the proposed framework is simulated on the historical data of a small group of knowledge workers. The collected explicit feedback of participants on the made recommendations from both their personal and corporate information space indicate that while the approach is promising (with 54% accuracy in recommending relevant information items), there is still considerable potential for improvement in filtering out noise and better modeling user contexts and information needs.
  • Konferenzbeitrag
    Using Large Language Models to Generate Authentic Multi-agent Knowledge Work Datasets
    (INFORMATIK 2024, 2024) Heim, Desiree; Jilek, Christian; Ulges, Adrian; Dengel, Andreas
    Current publicly available knowledge work data collections lack diversity, extensive annotations, and contextual information about the users and their documents. These issues hinder objective and comparable data-driven evaluations and optimizations of knowledge work assistance systems. Due to the considerable resources needed to collect such data in real-life settings and the necessity of data censorship, collecting such a dataset appears nearly impossible. For this reason, we propose a configurable, multi-agent knowledge work dataset generator. This system simulates collaborative knowledge work among agents producing Large Language Model-generated documents and accompanying data traces. Additionally, the generator captures all background information, given in its configuration or created during the simulation process, in a knowledge graph. Finally, the resulting dataset can be utilized and shared without privacy or confidentiality concerns. This paper introduces our approach’s design and vision and focuses on generating authentic knowledge work documents using Large Language Models. Our study involving human raters who assessed 53% of the generated and 74% of the real documents as realistic demonstrates the potential of our approach. Furthermore, we analyze the authenticity criteria mentioned in the participants’ comments and elaborate on potential improvements for identified common issues.