KSKilian Sprenkamp

Kilian Sprenkamp

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Kilian Sprenkamp has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Guidelines for employing large language models in information systems research

    by Kilian Sprenkamp, Kazem Haki, Liudmila Zavolokina

  • Open Access

    From Information-Seeking to Information-Asking: Designing RefuGPT, a Chatbot for Ukrainian Refugees in Switzerland

    by Kilian Sprenkamp, Sven Eckhardt, Liudmila Zavolokina, Gerhard Schwabe

    A key challenge for refugees is accessing relevant information about their host country. However, refugees often face disorientation during their information-seeking process. Disorientation is driven by language barriers, a digital divide, high urgency, and an evolving situation, which hinders the refugees’ ability to access information. Addressing the issue of disorientation, we propose an IT artifact, i.e., a chatbot called RefuGPT , designed through a rigorous Design Science Research Methodology. RefuGPT leverages the power of a large language model (LLM), GPT-4 while accessing two distinct sources of information, i.e., official and community-based information utilizing retrieval augmented generation and prompt-based learning (Figure 1 ). We assess RefuGPT's usefulness and usability through an ex-post evaluation in a naturalistic setting with Ukrainian refugees. Hence, we show that our bi-layered LLM-based chatbot can effectively assist refugees. They thus move from information-seeking to a more effortless information-asking. Based on those insights, we propose design principles as well as practical recommendations for refugee chatbots.


  • Open Access

    Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking

    by Nicolas Hoferer, Kilian Sprenkamp, Dorian Christoph Quelle, Daniel Gordon Jones, Zoya Katashinskaya, Alexandre Bovet, Liudmila Zavolokina


  • Open Access

    Using Large Language Models for the Assessment of Sustainable Forest Investment Projects

    by Maria Letizia Jannibelli, Jiayu Luo, Kilian Sprenkamp, Liudmila Zavolokina

    The integration of Large Language Models (LLMs) into the assessment processes of sustainable forest investment projects is a compelling prospect, given the limitations present in manual assessment. This paper examines how such an LLM-based assessment tool can be designed and whether such a tool can serve as a viable alternative to human experts in this task through the development and subsequent evaluation of a prototype. The analysis shows that the use of retrieval augmented generation to extract and summarize relevant information from project documents is promising but reveals challenges in the use of LLMs for more complex analysis and grading tasks. Design principles and possible steps for further development of the tool are proposed.


  • Open Access

    Overcoming intergovernmental data sharing challenges with federated learning

    by Kilian Sprenkamp, Joaquín Delgado Fernández, Sven Eckhardt, Liudmila Zavolokina

    Intergovernmental collaboration is needed to address global problems. Modern solutions to these problems often include data-driven methods like artificial intelligence (AI), which require large amounts of data to perform well. As AI emerges as a central catalyst in deriving effective solutions for global problems, the infrastructure that supports its data needs becomes crucial. However, data sharing between governments is often constrained due to socio-technical barriers such as concerns over data privacy, data sovereignty issues, and the risks of information misuse. Federated learning (FL) presents a promising solution as a decentralized AI methodology, enabling the use of data from multiple silos without necessitating central aggregation. Instead of sharing raw data, governments can build their own models and just share the model parameters with a central server aggregating all parameters, resulting in a superior overall model. By conducting a structured literature review, we show how major intergovernmental data-sharing challenges listed by the Organisation for Economic Co-operation and Development can be overcome by utilizing FL. Furthermore, we provide a tangible resource implementing FL linked to the Ukrainian refugee crisis that can be utilized by researchers and policymakers alike who want to implement FL in cases where data cannot be shared. Enhanced AI while maintaining privacy through FL thus allows governments to collaboratively address global problems, positively impacting governments and citizens.


  • Open Access

    Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool

    by Liudmila Zavolokina, Kilian Sprenkamp, Zoya Katashinskaya, Daniel Gordon Jones, Gerhard Schwabe

    In today's digital age, characterized by rapid news consumption and increasing vulnerability to propaganda, fostering citizens' critical thinking is crucial for stable democracies. This paper introduces the design of ClarifAI, a novel automated propaganda detection tool designed to nudge readers towards more critical news consumption by activating the analytical mode of thinking, following Kahneman's dual-system theory of cognition. Using Large Language Models, ClarifAI detects propaganda in news articles and provides context-rich explanations, enhancing users' understanding and critical thinking. Our contribution is threefold: first, we propose the design of ClarifAI; second, in an online experiment, we demonstrate that this design effectively encourages news readers to engage in more critical reading; and third, we emphasize the value of explanations for fostering critical thinking. The study thus offers both a practical tool and useful design knowledge for mitigating propaganda in digital news.


  • Open Access

    Large Language Models for Propaganda Detection

    by Kilian Sprenkamp, Daniel Gordon Jones, Liudmila Zavolokina

    The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual dependencies. To address this issue, we investigate the effectiveness of modern Large Language Models (LLMs) such as GPT-3 and GPT-4 for propaganda detection. We conduct experiments using the SemEval-2020 task 11 dataset, which features news articles labeled with 14 propaganda techniques as a multi-label classification problem. Five variations of GPT-3 and GPT-4 are employed, incorporating various prompt engineering and fine-tuning strategies across the different models. We evaluate the models' performance by assessing metrics such as $F1$ score, $Precision$, and $Recall$, comparing the results with the current state-of-the-art approach using RoBERTa. Our findings demonstrate that GPT-4 achieves comparable results to the current state-of-the-art. Further, this study analyzes the potential and challenges of LLMs in complex tasks like propaganda detection.


  • Open Access

    Data-Driven Governance in Crises: Topic Modelling for the Identification of Refugee Needs

    by Kilian Sprenkamp, Liudmila Zavolokina, Mario Angst, Mateusz Dolata

    The war in Ukraine and the following refugee crisis have recently again highlighted the need for effective refugee management across European countries. Refugee management contemporarily mostly relies on top-down management approaches by governments. These often lead to suboptimal policies for refugees and highlight a need to better identify and integrate refugee needs into management. Here, we show that modern applications of Natural Language Processing (NLP) allow for the effective analysis of large text corpora linked to refugee needs, making it possible to complement top-down approaches with bottom-up knowledge centered around the current needs of the refugee population. By following a Design Science Research Methodology, we utilize 58 semi-structured stakeholder interviews within Switzerland to develop design requirements for NLP applications for refugee management. Based on the design requirements, we developed R2G – “Refugees to Government”, an application based on state-of-the-art topic modeling to identify refugee needs bottom-up through Telegram data. We evaluate R2G with a dedicated workshop held with stakeholders from the public sector and civil society. Thus, we contribute to the ongoing discourse on how to design refugee management applications and showcase how topic modeling can be utilized for data-driven governance during refugee crises.


  • Open Access

    Federated Learning as a Solution for Problems Related to Intergovernmental Data Sharing

    by Kilian Sprenkamp, Joaquin Delgado Fernandez, Sven Eckhardt, Liudmila Zavolokina

    To address global problems, intergovernmental collaboration is needed. Modern solutions to these problems often include data-driven methods like artificial intelligence (AI), which require large amounts of data to perform well. However, data sharing between governments is limited. A possible solution is federated learning (FL), a decentralised AI method created to utilise personal information on edge devices. Instead of sharing data, governments can build their own models and just share the model parameters with a centralised server aggregating all parameters, resulting in a superior overall model. By conducting a structured literature review, we show how major intergovernmental data sharing challenges like disincentives, legal and ethical issues as well as technical constraints can be solved through FL. Enhanced AI while maintaining privacy through FL thus allows governments to collaboratively address global problems, which will positively impact governments and citizens.


  • Open Access

    Citizens' Expectations about Achieving Public Value and the Role of Digital Technologies: It Takes Three to Tango!

    by Liudmila Zavolokina, Kilian Sprenkamp, Birgit Schenk

    Governments across the globe are facing pressure to increase the speed of their digital transformation to meet the needs of the digital society while fulfilling their primary task of delivering public value. While researchers agree on the importance of the public sector for public value creation, recently, more and more studies have recognized the criticality of collaboration between the public and private sectors for successful public value creation. In our research, we conduct a qualitative survey. We examine the idea of collaboration between the public and the private sectors in more detail and extend it from a citizens’ perspective. We highlight the need for joint forces for optimal public value creation and identify ways to achieve this and what digital technologies can support this process.